© 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. 9997
    Prev
    Next
    INDEX
    Explanations

    number sequences associated with codenames or specific terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific measures, indicators, or items identified by numerical designations

    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
    909
    -0.92
    529
    -0.82
    vier
    -0.77
    537
    -0.75
    727
    -0.74
    528
    -0.73
    880
    -0.72
    916
    -0.72
    627
    -0.71
    usky
    -0.71
    POSITIVE LOGITS
    âĢ²
    0.83
     itself
    0.78
    âĢ³
    0.72
     deficiency
    0.72
     comprises
    0.68
     datas
    0.65
     contains
    0.62
     onwards
    0.62
     Sabha
    0.62
     Specifications
    0.61
    Activations Density 0.173%

    No Known Activations