Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34145
    Prev
    Next
    INDEX
    Explanations

    text containing a mix of non-English characters and English alphabets, likely with no specific theme or specific language

    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
    284
    +0.16
    0.7%
    699
    +0.14
    0.6%
    52
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.16
    0.11
    274
    +0.14
    0.10
    228
    +0.13
    0.10
    Negative Logits
    hiba
    -0.91
    earchers
    -0.91
    aque
    -0.83
    uberty
    -0.81
    pering
    -0.81
    voy
    -0.80
    utenberg
    -0.80
    oute
    -0.78
    staking
    -0.77
    asus
    -0.77
    POSITIVE LOGITS
    е
    1.40
    а
    1.40
    о
    1.28
    и
    1.28
    оÐ
    1.24
    Ñĭ
    1.21
    л
    1.10
    н
    1.09
    Ñĥ
    1.08
    ÑĢ
    1.06
    Activations Density 4.771%

    No Known Activations