© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 17526
    Prev
    Next
    INDEX
    Explanations

    instances of people being accompanied by others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accompanied" and similar verbs indicating companionship or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Origin
    -0.67
     comprom
    -0.65
    urai
    -0.62
     leverage
    -0.61
     leftover
    -0.57
     allowable
    -0.56
     Reconstruction
    -0.56
     exploited
    -0.55
     exploiting
    -0.55
     coercive
    -0.54
    POSITIVE LOGITS
    by
    1.22
     by
    1.17
    By
    0.93
    igious
    0.86
    bys
    0.86
     BY
    0.85
    idable
    0.85
    BY
    0.84
    Ń·
    0.83
    ĸļ
    0.81
    Activations Density 0.144%

    No Known Activations