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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18501
    Prev
    Next
    INDEX
    Explanations

    phrases identifying specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals specifically using the word "himself," "herself," or "themselves."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onal
    -0.83
    olid
    -0.71
    ysical
    -0.70
    CLOSE
    -0.69
    SHIP
    -0.66
     Frenzy
    -0.63
     convergence
    -0.63
    ammy
    -0.62
     RELEASE
    -0.61
    odies
    -0.60
    POSITIVE LOGITS
     admitted
    0.94
     confessed
    0.88
     admits
    0.86
     acknowledged
    0.84
    é¾įåĸļ士
    0.81
     conceded
    0.77
     penned
    0.77
     profess
    0.75
     doubted
    0.74
     contradicted
    0.74
    Activations Density 0.039%

    No Known Activations