© 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. 36417
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of 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
    201
    +0.10
    0.5%
    236
    +0.10
    0.5%
    437
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.22
    288
    +0.10
    0.21
    683
    +0.10
    0.09
    Negative Logits
    ers
    -0.85
    furt
    -0.78
    ued
    -0.75
    ees
    -0.71
    rooms
    -0.70
    ered
    -0.70
    uing
    -0.69
    ership
    -0.68
    ez
    -0.67
    erness
    -0.64
    POSITIVE LOGITS
    ãĥ¥
    0.65
    ©¶æ
    0.64
    onica
    0.61
    ailability
    0.61
    pered
    0.61
     earthqu
    0.60
    geon
    0.59
     grounding
    0.59
    é¾
    0.58
    dain
    0.58
    Activations Density 7.432%

    No Known Activations