© 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. 39675
    Prev
    Next
    INDEX
    Explanations

    references to controversial or provocative statements related to politics or current events

    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
    199
    +0.10
    0.6%
    214
    +0.08
    0.5%
    247
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.10
    0.13
    536
    +0.08
    0.08
    23
    +0.08
    0.10
    Negative Logits
    minster
    -0.64
    ulhu
    -0.62
    senal
    -0.51
    nces
    -0.47
    silver
    -0.47
    Si
    -0.46
    Brave
    -0.45
    Bu
    -0.45
    PLA
    -0.45
    è£ħ
    -0.44
    POSITIVE LOGITS
    ealous
    0.64
    agog
    0.63
    xual
    0.60
    oned
    0.59
    ager
    0.57
    gment
    0.56
    uled
    0.56
    adows
    0.56
    whel
    0.56
    arded
    0.56
    Activations Density 6.716%

    No Known Activations