© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1652
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names from different fields, including people, places, and events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    627
    +0.21
    0.7%
    640
    +0.18
    0.6%
    447
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.21
    0.12
    627
    +0.18
    0.09
    640
    +0.16
    0.13
    Negative Logits
     incon
    -1.24
     versa
    -0.98
    pection
    -0.98
     inflamm
    -0.95
     unman
    -0.95
     cere
    -0.94
     airspace
    -0.94
     traps
    -0.93
     antioxid
    -0.93
     evapor
    -0.92
    POSITIVE LOGITS
    aka
    1.62
    formerly
    1.32
    alias
    1.28
    pron
    1.25
    pictured
    1.23
     aka
    1.17
    ä¸
    1.13
    bath
    1.11
    YY
    1.10
    SHA
    1.08
    Activations Density 1.818%

    No Known Activations