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

    Neuronpedia

    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. 14446
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities or aspects

    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
    30
    +0.03
    0.5%
    104
    +0.03
    0.5%
    756
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.03
    0.01
    756
    +0.03
    -0.01
    243
    +0.03
    0.01
    Negative Logits
    ridge
    -0.19
    Brexit
    -0.18
    annabin
    -0.18
    âĦ¢:
    -0.17
    spring
    -0.16
    hya
    -0.16
    dylib
    -0.15
    rise
    -0.15
    mph
    -0.15
    hire
    -0.15
    POSITIVE LOGITS
    Sov
    0.17
    anwhile
    0.17
     beforehand
    0.16
     backward
    0.15
     guiName
    0.15
     prin
    0.15
     icing
    0.15
     tyr
    0.15
    ²¾
    0.15
    uddin
    0.15
    Activations Density 0.050%

    No Known Activations