© 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. 40793
    Prev
    Next
    INDEX
    Explanations

    parts of text discussing contrast between two opposing sides or parts

    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
    +0.12
    0.7%
    246
    +0.10
    0.5%
    567
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.12
    0.22
    447
    +0.10
    0.25
    64
    +0.08
    -0.26
    Negative Logits
    DERR
    -0.64
    IVERS
    -0.64
    DOS
    -0.61
    quickShipAvailable
    -0.59
    DEF
    -0.59
    ت
    -0.56
    س
    -0.56
    اÙĦ
    -0.55
    Acknowled
    -0.55
    ãĤ¼ãĤ¦ãĤ¹
    -0.54
    POSITIVE LOGITS
     apiece
    0.72
    ilion
    0.61
     individually
    0.60
    undred
    0.57
     each
    0.56
     stroke
    0.55
    fecture
    0.55
     parcel
    0.54
     swoop
    0.54
    abyte
    0.52
    Activations Density 15.681%

    No Known Activations