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. 17028
    Prev
    Next
    INDEX
    Explanations

    terms related to sports or athletics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to athletics and athletic programs

    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
    ãĥĢ
    -0.87
    later
    -0.73
    enthal
    -0.71
    ered
    -0.68
    places
    -0.67
    heit
    -0.63
    atche
    -0.62
    amn
    -0.62
    ilts
    -0.60
     Salmon
    -0.60
    POSITIVE LOGITS
    letes
    0.89
     scholarships
    0.85
     trainers
    0.83
     trainer
    0.82
     pursuits
    0.80
     directors
    0.80
     department
    0.79
     commissions
    0.78
    lete
    0.78
    limits
    0.76
    Activations Density 0.042%

    No Known Activations