© 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. 32873
    Prev
    Next
    INDEX
    Explanations

    words related to searching, seeking, or looking and phrases related to challenges or obstacles

    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
    447
    +0.23
    1.0%
    514
    +0.10
    0.4%
    501
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.23
    0.29
    23
    +0.10
    0.26
    68
    +0.10
    0.19
    Negative Logits
     GPS
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
     Calculator
    -0.69
    çIJ
    -0.69
     depressed
    -0.67
    iewicz
    -0.67
     Zy
    -0.66
     radar
    -0.65
    ãĢIJ
    -0.65
     Samar
    -0.64
    POSITIVE LOGITS
    sure
    0.91
    should
    0.86
    £
    0.86
    must
    0.86
    dro
    0.83
    ¡
    0.82
    ¢
    0.82
    thus
    0.82
    tu
    0.78
    _.
    0.77
    Activations Density 10.417%

    No Known Activations