© 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 Local
    9. 6-RES_SCL-AJT
    11. 33274
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
    649
    +0.06
    0.5%
    756
    +0.06
    0.5%
    667
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.06
    0.10
    110
    +0.06
    0.09
    326
    +0.06
    0.24
    Negative Logits
    lihood
    -0.41
     medication
    -0.40
     tickets
    -0.39
     loopholes
    -0.38
    drm
    -0.38
    math
    -0.37
     medications
    -0.37
    Db
    -0.36
     prescriptions
    -0.36
     aisle
    -0.34
    POSITIVE LOGITS
    eer
    0.67
    uebl
    0.58
    eers
    0.56
    oing
    0.53
    oes
    0.46
    atl
    0.46
     Gree
    0.46
    utsche
    0.44
    olithic
    0.44
    oan
    0.43
    Activations Density 10.858%

    No Known Activations