© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31653
    Prev
    Next
    INDEX
    Explanations

    narratives centered around personal reflection and self-awareness

    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
    373
    +0.17
    1.1%
    218
    +0.14
    0.9%
    762
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.17
    0.23
    526
    +0.14
    -0.03
    570
    +0.12
    0.04
    Negative Logits
    ortium
    -0.58
    surprisingly
    -0.56
     ®
    -0.56
    orically
    -0.51
     unsurprisingly
    -0.51
    bitious
    -0.51
    atform
    -0.50
    ourse
    -0.49
    odox
    -0.49
    umerous
    -0.49
    POSITIVE LOGITS
     fuckin
    0.92
    ..."
    0.88
    âĢ¦"
    0.81
     âĢ¦"
    0.79
    )."
    0.78
     ..."
    0.75
    âĢ¦."
    0.74
    .'"
    0.74
     gonna
    0.73
    -"
    0.71
    Activations Density 7.799%

    No Known Activations