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. 11-RES-JB
    6. 8715
    Prev
    Next
    INDEX
    Explanations

    quotations enclosed in double quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and phrases indicating excitement or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    949
    -0.74
    riott
    -0.73
    ãĥª
    -0.73
    arl
    -0.71
    oint
    -0.70
    arian
    -0.69
    Sil
    -0.68
    urrent
    -0.68
    arrell
    -0.68
    ully
    -0.67
    POSITIVE LOGITS
     Go
    1.93
    Go
    1.80
    go
    1.79
     GO
    1.70
     go
    1.56
    GO
    1.47
     Goo
    1.33
     gone
    1.24
     Goes
    1.17
     went
    1.12
    Activations Density 0.155%

    No Known Activations