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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22844
    Prev
    Next
    INDEX
    Explanations

    phrases related to offensive language or behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to offensive content or material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chell
    -0.92
    perature
    -0.68
    igrate
    -0.68
    hett
    -0.67
    population
    -0.67
    plates
    -0.66
    uther
    -0.66
    ho
    -0.65
    clerosis
    -0.65
    ãĤ£
    -0.64
    POSITIVE LOGITS
    thouse
    0.73
    bringer
    0.70
     thrust
    0.67
     Hebdo
    0.66
    ments
    0.65
     insensitive
    0.65
     humour
    0.64
     Cartoon
    0.64
     Wilde
    0.63
    ingly
    0.61
    Activations Density 0.045%

    No Known Activations