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. 8-RES-JB
    6. 21152
    Prev
    Next
    INDEX
    Explanations

    mentions of political or societal issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character used in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sled
    -0.75
     cottage
    -0.69
     Manhattan
    -0.66
     coat
    -0.64
     unmarked
    -0.63
     Somerset
    -0.61
     cloak
    -0.61
     coats
    -0.61
     regist
    -0.60
    isode
    -0.59
    POSITIVE LOGITS
    ¬
    1.20
    º
    0.92
    ½
    0.92
    ¡
    0.92
    £
    0.92
    ¥
    0.91
    ľ
    0.91
    ¾
    0.90
    Ĵ
    0.88
    ¼
    0.88
    Activations Density 0.329%

    No Known Activations