© 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. 0-RES-JB
    11. 16942
    Prev
    Next
    INDEX
    Explanations

    spam-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to spam and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strument
    -0.78
    gerald
    -0.78
    stained
    -0.74
    rey
    -0.71
    SPONSORED
    -0.70
     Upton
    -0.67
    rift
    -0.64
    spect
    -0.64
    hend
    -0.63
    environment
    -0.63
    POSITIVE LOGITS
     spam
    2.13
     CAN
    1.59
     Abuse
    1.33
    akov
    1.28
    CAN
    1.27
    pload
    1.10
    ammers
    1.09
    imov
    1.06
     Pascal
    1.05
     Bots
    0.99
    Activations Density 0.043%

    No Known Activations