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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 12840
    Prev
    Next
    INDEX
    Explanations

    statements where someone is quoted or reported speaking or providing information

    oai_token-act-pair · gpt-3.5-turbo

    statements made by individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otin
    -1.04
    hook
    -0.78
    weed
    -0.76
    Honest
    -0.73
    etsy
    -0.70
    bum
    -0.70
    idge
    -0.69
    pee
    -0.68
    artist
    -0.68
    gregation
    -0.65
    POSITIVE LOGITS
    istani
    0.90
     Pesh
    0.82
     YPG
    0.80
     Tehran
    0.77
     Riyadh
    0.74
     quoting
    0.74
     Ago
    0.74
    igun
    0.74
     Iranian
    0.73
     Mahm
    0.73
    Activations Density 0.195%

    No Known Activations