© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    skills or items in fantasy role-playing games

    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
    110
    +0.07
    0.6%
    311
    +0.07
    0.6%
    101
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.27
    316
    +0.07
    0.10
    343
    +0.06
    0.09
    Negative Logits
    ervatives
    -0.50
    pread
    -0.50
    overs
    -0.46
    ervative
    -0.44
    opausal
    -0.42
    oin
    -0.42
    arat
    -0.40
    othal
    -0.40
     Wage
    -0.40
    erate
    -0.39
    POSITIVE LOGITS
    glers
    0.49
    ENC
    0.47
     Identified
    0.45
     describ
    0.39
     este
    0.39
    âĵĺ
    0.38
    REE
    0.38
     Provided
    0.37
     plaque
    0.36
     corrid
    0.36
    Activations Density 12.629%

    No Known Activations