© 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. 1-RES-JB
    11. 20001
    Prev
    Next
    INDEX
    Explanations

    spam-related keywords or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to spam and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hani
    -0.83
    姫
    -0.73
     Became
    -0.67
     Cel
    -0.67
     Heb
    -0.65
     Rite
    -0.64
     Mart
    -0.64
     Vernon
    -0.63
     Patri
    -0.61
    Beck
    -0.61
    POSITIVE LOGITS
     spam
    1.23
    ming
    1.14
    inator
    0.89
    ulent
    0.82
    vertising
    0.81
    ulence
    0.81
    ular
    0.81
    ulus
    0.79
    bugs
    0.79
     bots
    0.78
    Activations Density 0.007%

    No Known Activations