© 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. 15165
    Prev
    Next
    INDEX
    Explanations

    words related to specific professions or specific scenarios involving those professions

    oai_token-act-pair · gpt-3.5-turbo

    elements associated with authority figures and societal structures

    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
    urations
    -0.74
     Dover
    -0.69
    sequ
    -0.67
    KC
    -0.64
     respectively
    -0.59
     Codex
    -0.57
    ophon
    -0.55
     Ply
    -0.55
     Simpl
    -0.54
    ollow
    -0.54
    POSITIVE LOGITS
     knows
    0.92
     dies
    0.89
     thinks
    0.88
     who
    0.88
    who
    0.85
     decides
    0.84
     masturb
    0.84
     whom
    0.83
     wears
    0.81
     wants
    0.80
    Activations Density 0.766%

    No Known Activations