© 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. 3941
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blow" in various contexts

    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
    +0.14
    0.5%
    553
    +0.12
    0.5%
    203
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.08
    34
    +0.12
    0.06
    203
    +0.11
    0.07
    Negative Logits
    ç«
    -0.86
    ordan
    -0.83
    ript
    -0.81
    ournal
    -0.81
    ately
    -0.80
    iosity
    -0.80
    ently
    -0.78
    abolic
    -0.76
    Definition
    -0.75
     guiIcon
    -0.74
    POSITIVE LOGITS
    guns
    1.13
    gun
    1.02
    outs
    1.02
     holes
    1.00
    out
    0.99
    holes
    0.99
    job
    0.97
    pipe
    0.94
    bang
    0.94
    blown
    0.92
    Activations Density 8.748%

    No Known Activations