© 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. 35589
    Prev
    Next
    INDEX
    Explanations

    WORDS IN A DIFFERENT ALPHABET OR LANGUAGE

    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
    70
    +0.10
    0.5%
    326
    +0.10
    0.5%
    45
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.10
    0.08
    70
    +0.10
    0.08
    160
    +0.10
    0.12
    Negative Logits
    iaries
    -1.08
    iary
    -0.95
    essa
    -0.83
    erry
    -0.80
    arching
    -0.78
    iance
    -0.70
    espie
    -0.70
    acles
    -0.70
    oubted
    -0.69
    olphin
    -0.69
    POSITIVE LOGITS
    м
    0.96
    л
    0.91
    к
    0.91
    ÑĤ
    0.89
    е
    0.86
    Ð
    0.86
     Disorders
    0.83
    Ñģ
    0.82
    Ñ
    0.80
    ãĤ§
    0.77
    Activations Density 4.923%

    No Known Activations