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. 22688
    Prev
    Next
    INDEX
    Explanations

    references to specific highways or locations

    oai_token-act-pair · gpt-3.5-turbo

    specific highway or route numbers

    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
    iques
    -0.66
     nom
    -0.63
     suggestions
    -0.63
     WikiLeaks
    -0.61
    onic
    -0.60
     Ps
    -0.60
    orians
    -0.59
    hetical
    -0.59
     leaps
    -0.58
     term
    -0.58
    POSITIVE LOGITS
    01
    0.96
    XX
    0.94
    A
    0.91
    RH
    0.90
    CV
    0.89
    XXX
    0.89
    B
    0.88
    503
    0.86
    70
    0.85
    002
    0.85
    Activations Density 0.065%

    No Known Activations