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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2585
    Prev
    Next
    INDEX
    Explanations

    medical specialty terms, country names, city names, specific professions, and product details

    oai_token-act-pair · gpt-3.5-turbo

    references to specific fields or areas of study, particularly in medicine and academia

    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
    endif
    -0.71
     otherwise
    -0.68
     somew
    -0.66
    else
    -0.64
    "))
    -0.62
    SPONSORED
    -0.59
     nevertheless
    -0.57
    ))))
    -0.57
    etimes
    -0.56
     subsequent
    -0.56
    POSITIVE LOGITS
    ®,
    1.13
    *,
    1.00
    (),
    0.94
     (),
    0.88
    ,[
    0.85
    ,
    0.84
    !,
    0.79
    ;
    0.78
     ,
    0.77
     ($
    0.77
    Activations Density 0.782%

    No Known Activations