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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 13530
    Prev
    Next
    INDEX
    Explanations

    information related to technological components and specifications

    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
    +0.22
    1.3%
    541
    +0.10
    0.6%
    497
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.22
    0.17
    512
    +0.10
    0.12
    762
    +0.09
    0.20
    Negative Logits
    otiation
    -0.54
     decree
    -0.52
     Toledo
    -0.52
    alis
    -0.49
     surgeries
    -0.47
    redo
    -0.46
     facade
    -0.46
     skyline
    -0.46
     Recon
    -0.45
     Globe
    -0.44
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.69
     "â̦
    0.64
    ITNESS
    0.64
     "'
    0.64
    ItemImage
    0.62
     influenced
    0.60
    imilar
    0.58
    STEM
    0.58
    rael
    0.57
    inventoryQuantity
    0.57
    Activations Density 10.951%

    No Known Activations