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. 1-RES-JB
    6. 19530
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific phrases related to various fields of interest or expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, titles, or identifiers related to popular culture and entertainment

    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
    EStream
    -0.82
    EStreamFrame
    -0.79
    DragonMagazine
    -0.74
    enance
    -0.74
    bleacher
    -0.72
    tumblr
    -0.71
    eering
    -0.69
     Chronicle
    -0.65
    rior
    -0.65
    PLA
    -0.63
    POSITIVE LOGITS
     unden
    0.89
     metic
    0.81
    ¨
    0.75
    ĩ
    0.73
     advoc
    0.72
     conduc
    0.71
    ahon
    0.71
     redes
    0.71
     lightweight
    0.69
     airline
    0.66
    Activations Density 2.176%

    No Known Activations