© 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 Local
    9. 6-RES_SCL-AJT
    11. 12949
    Prev
    Next
    INDEX
    Explanations

    and highlight specific phrases or words within sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.24
    1.0%
    562
    +0.12
    0.5%
    745
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.24
    0.34
    193
    +0.12
    0.13
    640
    +0.11
    0.30
    Negative Logits
    nia
    -1.02
    IER
    -0.88
    Americ
    -0.85
    igent
    -0.82
     Tomato
    -0.76
    nos
    -0.75
    iom
    -0.74
    Norm
    -0.73
    iencies
    -0.73
    ANA
    -0.71
    POSITIVE LOGITS
     shove
    0.91
     cancel
    0.86
     exh
    0.86
     burn
    0.85
     withdraw
    0.84
     subtract
    0.84
     throw
    0.84
     coer
    0.84
     rein
    0.83
     conclud
    0.83
    Activations Density 21.145%

    No Known Activations