Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17298
    Prev
    Next
    INDEX
    Explanations

    terms related to financial markets or medical conditions where an injury requires a second treatment or action

    oai_token-act-pair · gpt-3.5-turbo

    references to secondary effects or markets

    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
    uge
    -0.82
    liness
    -0.80
    ===
    -0.77
    atche
    -0.75
    ============
    -0.73
    ername
    -0.72
    âĸĪâĸĪ
    -0.71
    estern
    -0.70
     Archdemon
    -0.70
     Tycoon
    -0.69
    POSITIVE LOGITS
    aband
    0.90
    secondary
    0.86
    ities
    0.83
    anguage
    0.83
    arily
    0.75
     mater
    0.74
     school
    0.70
    school
    0.70
     secondary
    0.69
     schooling
    0.69
    Activations Density 0.022%

    No Known Activations