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. 10-RES-JB
    6. 15508
    Prev
    Next
    INDEX
    Explanations

    names or terms related to various industries or fields of work

    oai_token-act-pair · gpt-3.5-turbo

    current trends and significant cultural or social themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.52
    rely
    -0.52
    ĪĴ
    -0.52
    pload
    -0.50
     pse
    -0.49
    vice
    -0.49
     MIS
    -0.48
    rocal
    -0.48
    ©¶æ
    -0.44
    eatures
    -0.44
    POSITIVE LOGITS
    .
    1.04
    ;
    0.98
     because
    0.97
     but
    0.97
    .[
    0.92
    ,[
    0.91
     although
    0.82
    ,''
    0.82
     whereas
    0.78
     despite
    0.77
    Activations Density 1.175%

    No Known Activations