© 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. 9-RES-JB
    11. 13254
    Prev
    Next
    INDEX
    Explanations

    words related to coding, software development, and technology

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to software and coding technologies

    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
     DOI
    -0.73
     surn
    -0.72
     grandchildren
    -0.71
     circumst
    -0.71
     hors
    -0.70
     undes
    -0.70
     grandson
    -0.68
     repealing
    -0.68
     marching
    -0.67
     homosexual
    -0.67
    POSITIVE LOGITS
    rix
    0.95
    ools
    0.93
    isoft
    0.93
    nergy
    0.92
    orks
    0.91
    Network
    0.91
    olve
    0.91
    ource
    0.89
    Platform
    0.89
    Tool
    0.89
    Activations Density 0.116%

    No Known Activations