© 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. 9-RES-JB
    11. 15372
    Prev
    Next
    INDEX
    Explanations

    words related to deception and manipulation, such as publicity stunts, hoaxes, fabrications, and conspiracies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deceptive or misleading actions

    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
    izont
    -0.94
    anamo
    -0.75
    upt
    -0.74
    enz
    -0.73
    liam
    -0.72
    acers
    -0.70
    arton
    -0.70
    pict
    -0.70
    »Ĵ
    -0.69
    accompan
    -0.67
    POSITIVE LOGITS
     concoct
    1.04
     perpetrated
    0.94
     ploy
    0.93
     shenan
    0.90
     rather
    0.88
     aimed
    0.86
     meant
    0.85
     gimmick
    0.83
     invented
    0.82
     diversion
    0.82
    Activations Density 0.355%

    No Known Activations