© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 32743
    Prev
    Next
    INDEX
    Explanations

    information related to saving things like money, lives, or day-to-day items

    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%
    747
    +0.14
    0.6%
    16
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    574
    +0.15
    0.01
    35
    +0.14
    0.06
    393
    +0.10
    0.23
    Negative Logits
    SPONSORED
    -1.05
    女
    -0.81
    Īè
    -0.73
    ranean
    -0.70
    lems
    -0.68
    æ©Ł
    -0.68
    çļ
    -0.67
    adal
    -0.67
    ç«
    -0.67
    alities
    -0.65
    POSITIVE LOGITS
     suspense
    0.80
     hassle
    0.73
     bacon
    0.72
     hostages
    0.70
     precious
    0.69
     penn
    0.69
     sanity
    0.69
     sake
    0.69
    anza
    0.68
     Lives
    0.67
    Activations Density 10.917%

    No Known Activations