© 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. 6-RES-JB
    11. 17026
    Prev
    Next
    INDEX
    Explanations

    references to illegal activities or wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal activities and offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    versely
    -0.74
    negie
    -0.72
    erella
    -0.72
    antage
    -0.72
    hetically
    -0.70
    yip
    -0.69
    historic
    -0.69
    itionally
    -0.68
    ificent
    -0.67
    icipated
    -0.67
    POSITIVE LOGITS
    ãĥīãĥ©
    0.95
    SpaceEngineers
    0.81
    glers
    0.77
    ãĤ¹ãĥĪ
    0.76
     syndrome
    0.72
    parts
    0.72
    icides
    0.69
    ãĤ®
    0.68
    LOAD
    0.66
    ãĥĥãĤ¯
    0.66
    Activations Density 0.325%

    No Known Activations