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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 10615
    Prev
    Next
    INDEX
    Explanations

    quotes within sentences indicated by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuated dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NZ
    -0.61
     ***
    -0.52
     brim
    -0.50
    ËĪ
    -0.47
    ãĤ´ãĥ³
    -0.44
    REDACTED
    -0.43
    brance
    -0.42
     ****
    -0.42
     Âł Âł
    -0.41
     aluminium
    -0.40
    POSITIVE LOGITS
    ,"
    2.87
    ),"
    2.83
    .,"
    2.74
    ,'"
    2.56
    ,''
    2.51
    ',"
    2.49
     ,"
    2.30
    "),
    2.20
    )",
    2.16
    ],"
    2.09
    Activations Density 0.099%

    No Known Activations