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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 361
    Prev
    Next
    INDEX
    Explanations

    keywords related to database operations and programming code

    oai_token-act-pair · gpt-3.5-turbo

    elements related to data structures and coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gearing
    -0.64
     incredibly
    -0.62
     detrim
    -0.61
    aeda
    -0.59
     empowering
    -0.58
     particularly
    -0.57
     exceptionally
    -0.57
     amazingly
    -0.57
     unbelievably
    -0.56
     prosecuting
    -0.56
    POSITIVE LOGITS
    _
    1.38
    info
    0.93
    Obj
    0.89
    @
    0.88
    ername
    0.87
    Data
    0.87
    Of
    0.86
    ctl
    0.86
    data
    0.85
    cmd
    0.85
    Activations Density 0.223%

    No Known Activations