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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34208
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terminology related to quantum computing and physics

    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
    0.6%
    651
    +0.13
    0.5%
    195
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.15
    0.20
    138
    +0.13
    0.18
    64
    +0.12
    -0.16
    Negative Logits
    HAEL
    -0.87
    zsche
    -0.83
    AGES
    -0.79
    ãĤ¹ãĥĪ
    -0.75
    ãĥł
    -0.75
     intens
    -0.74
     tolerate
    -0.73
     disparate
    -0.73
     wounding
    -0.71
    baugh
    -0.70
    POSITIVE LOGITS
    arantine
    1.26
    ipped
    1.19
    inoa
    1.17
    idd
    1.17
    arre
    1.12
    isition
    1.11
    icks
    1.11
    asar
    1.11
    oted
    1.09
    irk
    1.09
    Activations Density 8.090%

    No Known Activations