© 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. 32562
    Prev
    Next
    INDEX
    Explanations

    information related to politics and elections

    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
    +0.23
    1.6%
    218
    +0.09
    0.6%
    311
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.49
    64
    +0.09
    -0.30
    618
    +0.07
    0.24
    Negative Logits
    daq
    -0.51
     Berks
    -0.45
    boards
    -0.43
    minus
    -0.43
    bris
    -0.41
    nell
    -0.40
    hr
    -0.39
    board
    -0.39
    kel
    -0.39
    heet
    -0.38
    POSITIVE LOGITS
     Firstly
    0.70
    Firstly
    0.56
    âĹı
    0.47
    ecause
    0.46
     First
    0.44
     namely
    0.44
    FML
    0.44
    hemat
    0.44
     principled
    0.43
    SSL
    0.42
    Activations Density 18.636%

    No Known Activations