© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40704
    Prev
    Next
    INDEX
    Explanations

    various statements starting with "According to" and conveying information from different sources

    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
    +0.33
    1.3%
    68
    +0.15
    0.6%
    679
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.23
    559
    +0.15
    0.09
    94
    +0.15
    0.14
    Negative Logits
    estern
    -1.07
    blast
    -0.85
    apons
    -0.84
    obyl
    -0.79
    aden
    -0.78
    pez
    -0.77
    igers
    -0.76
    abs
    -0.75
    egg
    -0.75
    eg
    -0.73
    POSITIVE LOGITS
    Ĥİ
    0.87
    edly
    0.85
    Rank
    0.84
     sources
    0.83
    Sources
    0.81
    edIn
    0.80
    Style
    0.79
    Format
    0.79
    TION
    0.78
    ly
    0.77
    Activations Density 9.936%

    No Known Activations