© 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. 5556
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress, development, planning, instruction, teachings, and rules

    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
    640
    +0.17
    0.6%
    360
    +0.16
    0.5%
    385
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.13
    360
    +0.16
    0.11
    758
    +0.15
    0.10
    Negative Logits
    wagen
    -1.01
     Luxembourg
    -0.95
     shack
    -0.95
     dispers
    -0.94
     Bermuda
    -0.93
     detached
    -0.92
     shroud
    -0.91
     buggy
    -0.90
     cyan
    -0.90
     cottage
    -0.90
    POSITIVE LOGITS
    ¹
    1.69
    ¡
    1.50
    º
    1.49
    į
    1.49
    ª
    1.46
    £
    1.42
    ł
    1.41
    ĸļ
    1.39
    Į
    1.39
    ¤
    1.37
    Activations Density 0.795%

    No Known Activations