© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17217
    Prev
    Next
    INDEX
    Explanations

    mentions to subscribe to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or significant figures

    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
     CoC
    -0.68
     ASIC
    -0.65
     grounds
    -0.64
     SQ
    -0.64
     HM
    -0.62
     QC
    -0.61
     entirety
    -0.61
     Lodge
    -0.61
     FIR
    -0.60
     deceived
    -0.60
    POSITIVE LOGITS
    NPR
    0.83
    ccording
    0.79
    pmwiki
    0.78
     tiss
    0.75
    everal
    0.74
    ENS
    0.73
    itous
    0.69
    Morning
    0.69
    inav
    0.68
    esson
    0.67
    Activations Density 0.131%

    No Known Activations