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. 1918
    Prev
    Next
    INDEX
    Explanations

    advice or instructions within sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning professional behavior and decision-making in campaigns

    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
    Downloadha
    -0.78
    netflix
    -0.75
    yss
    -0.72
     Casual
    -0.66
     frig
    -0.65
     combustion
    -0.63
    eco
    -0.62
     helicop
    -0.61
    $$$$
    -0.61
    ournal
    -0.61
    POSITIVE LOGITS
     grapple
    0.90
     pursue
    0.83
     overcame
    0.82
     ponder
    0.82
     undertake
    0.79
     grapp
    0.78
     undertook
    0.78
    Accept
    0.77
     discuss
    0.77
    estone
    0.75
    Activations Density 0.197%

    No Known Activations