© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13865
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Penguin"

    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
    99
    +0.12
    0.6%
    218
    +0.12
    0.6%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.29
    326
    +0.12
    0.25
    99
    +0.10
    0.15
    Negative Logits
    oway
    -0.99
    raq
    -0.93
    iencies
    -0.91
    oric
    -0.91
    orically
    -0.90
    tails
    -0.86
    ors
    -0.85
    ANC
    -0.84
    ouri
    -0.84
    tail
    -0.83
    POSITIVE LOGITS
     Clicker
    0.71
     Clause
    0.66
    liga
    0.61
     gorilla
    0.60
     ASC
    0.59
     tabl
    0.59
     bananas
    0.58
     pengu
    0.58
     bunny
    0.57
     jog
    0.57
    Activations Density 9.310%

    No Known Activations