© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32938
    Prev
    Next
    INDEX
    Explanations

    various special characters, possibly related to a specific language or coding syntax

    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
    116
    +0.13
    0.5%
    578
    +0.11
    0.4%
    587
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.16
    385
    +0.11
    0.16
    448
    +0.10
    0.07
    Negative Logits
    shire
    -0.94
    sburg
    -0.84
    giving
    -0.76
    sburgh
    -0.75
    swer
    -0.73
     Ago
    -0.73
    ¿½
    -0.72
    axter
    -0.71
    gdala
    -0.69
    elson
    -0.69
    POSITIVE LOGITS
    ģ«
    1.15
    ²¾
    1.02
    zynski
    0.98
    rating
    0.95
    ©¶æ¥µ
    0.92
    rats
    0.90
    ram
    0.88
    quer
    0.87
    ulture
    0.87
    prus
    0.86
    Activations Density 8.502%

    No Known Activations