© 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. 5564
    Prev
    Next
    INDEX
    Explanations

    expressions of exhaustion or frustration

    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
    288
    +0.23
    0.8%
    326
    +0.23
    0.8%
    85
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.23
    0.09
    288
    +0.23
    0.10
    85
    +0.15
    0.06
    Negative Logits
    iola
    -1.16
    izations
    -1.02
    byter
    -1.02
    authorized
    -1.00
    ection
    -0.96
    tein
    -0.93
    hips
    -0.93
    Team
    -0.93
    女
    -0.93
    Executive
    -0.92
    POSITIVE LOGITS
    igue
    1.56
    rums
    1.27
     tired
    1.02
     clich
    0.98
    ness
    0.98
    algia
    0.98
    entimes
    0.95
     stale
    0.94
    sbm
    0.93
     Takeru
    0.93
    Activations Density 1.310%

    No Known Activations