© 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. 40653
    Prev
    Next
    INDEX
    Explanations

    references to various types of publications, such as books, articles, and shows

    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
    9
    +0.04
    0.6%
    565
    +0.04
    0.6%
    373
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    589
    +0.04
    0.07
    362
    +0.04
    0.09
    373
    +0.03
    -0.18
    Negative Logits
    ĸļ
    -0.20
    ymes
    -0.20
    ¯
    -0.20
    ²¾
    -0.20
    ħĭ
    -0.19
    ////
    -0.19
     Arrows
    -0.19
    =-=-
    -0.19
    ¦
    -0.18
    VERTISEMENT
    -0.18
    POSITIVE LOGITS
    anamo
    0.21
    sels
    0.20
    court
    0.19
     NCT
    0.19
    abytes
    0.19
    gom
    0.18
    istor
    0.18
     expire
    0.18
    ocre
    0.18
    theless
    0.18
    Activations Density 8.474%

    No Known Activations