© 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 EvalsExportsinterp-engineNEWAPI 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. 31986
    Prev
    Next
    INDEX
    Explanations

    arguments presenting two contrasting possibilities or choices

    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
    +0.17
    1.1%
    393
    +0.10
    0.6%
    481
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.33
    561
    +0.10
    0.13
    473
    +0.07
    0.06
    Negative Logits
    advertisement
    -0.50
     Pony
    -0.48
    PLIC
    -0.47
    Cod
    -0.45
    rocket
    -0.44
    ENE
    -0.43
    Ĥİ
    -0.43
    pire
    -0.42
    oft
    -0.42
    STR
    -0.42
    POSITIVE LOGITS
     alternatively
    0.81
    acle
    0.77
    chard
    0.77
     else
    0.75
    Else
    0.71
    acles
    0.70
    chid
    0.70
    nam
    0.66
     otherwise
    0.64
    acular
    0.57
    Activations Density 13.464%

    No Known Activations