© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    technical details and comparisons between technology products, especially related to processors and their performance characteristics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.14
    0.5%
    434
    +0.12
    0.4%
    760
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.14
    0.05
    236
    +0.12
    0.07
    679
    +0.12
    0.11
    Negative Logits
    iffe
    -0.80
    adra
    -0.78
    HI
    -0.76
    azo
    -0.76
    Fif
    -0.75
    wings
    -0.74
    rha
    -0.74
    agall
    -0.74
    ogle
    -0.73
    enf
    -0.73
    POSITIVE LOGITS
     topics
    1.16
     fascinating
    1.07
     insights
    1.02
     curated
    1.01
     myths
    1.01
     reflections
    0.94
    podcast
    0.92
    how
    0.91
     podcast
    0.91
     Explore
    0.90
    Activations Density 3.521%

    No Known Activations