© 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. 4917
    Prev
    Next
    INDEX
    Explanations

    words related to items, properties, and attributes in a game or database with specific levels and features

    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
    139
    +0.03
    0.5%
    583
    +0.02
    0.5%
    203
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.03
    0.50
    160
    +0.02
    0.28
    64
    +0.02
    -0.36
    Negative Logits
    yip
    -0.17
    elsen
    -0.16
    Reply
    -0.15
    uv
    -0.15
    ebook
    -0.14
    uel
    -0.14
    vati
    -0.14
     RTX
    -0.14
     ax
    -0.14
    fp
    -0.14
    POSITIVE LOGITS
    =\"
    0.18
    ãĥ»
    0.17
     \\
    0.16
    ãĥª
    0.15
    ãĤ¹
    0.14
    \
    0.14
    ãĥĥãĥĪ
    0.14
    ì
    0.14
    itably
    0.14
    \.
    0.14
    Activations Density 23.219%

    No Known Activations