© 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. 32749
    Prev
    Next
    INDEX
    Explanations

    information related to a specific entity with the code 'SCP-665'

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.40
    3.9%
    64
    +0.17
    1.6%
    447
    +0.15
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.40
    0.92
    138
    +0.17
    0.92
    64
    +0.15
    -0.03
    Negative Logits
    ©¶æ
    -0.34
     ......
    -0.28
    ©¶æ¥µ
    -0.28
    interstitial
    -0.27
    20439
    -0.26
     calf
    -0.26
    é»Ĵ
    -0.26
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.26
    ãĥŁ
    -0.25
     adolesc
    -0.25
    POSITIVE LOGITS
    owship
    0.34
    raine
    0.32
    abs
    0.32
    ploy
    0.29
    obal
    0.29
    ness
    0.28
    inct
    0.28
    rench
    0.27
    ulo
    0.27
    ayne
    0.27
    Activations Density 1.271%

    No Known Activations