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. 40289
    Prev
    Next
    INDEX
    Explanations

    keywords related to textual content and data manipulation

    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
    609
    +0.13
    0.6%
    707
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.13
    -0.01
    45
    +0.11
    0.03
    137
    +0.11
    0.03
    Negative Logits
    Kin
    -0.88
    roxy
    -0.76
    ndra
    -0.76
    igun
    -0.74
    Statement
    -0.74
    jen
    -0.72
    Sov
    -0.71
    Resp
    -0.71
    Monitor
    -0.71
    illance
    -0.69
    POSITIVE LOGITS
     alphabet
    1.16
     letters
    1.07
     initials
    0.97
     spelling
    0.93
    ymes
    0.92
    acters
    0.88
     symbols
    0.87
     abbrevi
    0.83
     symbolism
    0.82
     hex
    0.82
    Activations Density 16.757%

    No Known Activations