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. 45102
    Prev
    Next
    INDEX
    Explanations

    human-readable text

    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
    +0.15
    0.7%
    102
    +0.13
    0.6%
    57
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    -0.03
    159
    +0.13
    0.10
    372
    +0.13
    0.09
    Negative Logits
    anwhile
    -0.80
     Plat
    -0.78
     Boone
    -0.76
     horizont
    -0.69
     Protector
    -0.69
     creators
    -0.69
    rawdownloadcloneembedreportprint
    -0.66
     GOODMAN
    -0.65
     Athens
    -0.65
     Macedonia
    -0.64
    POSITIVE LOGITS
    ĻĤ
    1.55
    ¥µ
    1.48
    ħĭ
    1.31
    Ĥª
    1.26
    ¥ŀ
    1.24
    ĪĴ
    1.21
    Ľ
    1.20
    ļ
    1.20
    Ķ
    1.15
    Ĭ
    1.13
    Activations Density 6.122%

    No Known Activations