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. 7-RES-JB
    6. 6742
    Prev
    Next
    INDEX
    Explanations

    common words related to technology and modernization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to entertainment and related media concepts

    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
    itans
    -0.68
     ---------
    -0.67
     Naples
    -0.66
     Wolfe
    -0.65
     Shepard
    -0.62
     Downing
    -0.61
     Leilan
    -0.61
    ModLoader
    -0.61
    FN
    -0.60
     Bulg
    -0.60
    POSITIVE LOGITS
    "
    1.15
    ",
    1.00
    "â̦
    0.99
    "-
    0.95
    "!
    0.94
    [/
    0.94
    "?
    0.94
    '?
    0.93
    "></
    0.93
    "—
    0.93
    Activations Density 0.301%

    No Known Activations