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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 7298
    Prev
    Next
    INDEX
    Explanations

    topics related to distribution, release, or dissemination of information or products

    oai_token-act-pair · gpt-3.5-turbo

    references to influential entities and their contexts in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.67
     summed
    -0.63
    CHAT
    -0.63
    imon
    -0.61
    orius
    -0.60
     Nanto
    -0.59
    iHUD
    -0.57
     explained
    -0.57
     recounted
    -0.55
     Sleeping
    -0.55
    POSITIVE LOGITS
     shelves
    1.23
     shores
    1.13
     doorstep
    0.98
     coffers
    0.95
     sooner
    0.93
     shelf
    0.90
    livion
    0.90
     arsen
    0.88
     fruition
    0.84
     throats
    0.84
    Activations Density 0.557%

    No Known Activations