© 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. 2040
    Prev
    Next
    INDEX
    Explanations

    profession or group names

    oai_token-act-pair · gpt-3.5-turbo

    collective identifiers for various groups of people

    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
     increments
    -0.61
     Chimera
    -0.60
    inventoryQuantity
    -0.60
     ESV
    -0.59
     Ratio
    -0.58
    bsp
    -0.58
     annexation
    -0.58
     SDL
    -0.57
    =~
    -0.57
     Prev
    -0.57
    POSITIVE LOGITS
     who
    1.17
     whom
    1.07
    who
    0.97
    hips
    0.93
    folk
    0.92
     whose
    0.86
     interviewed
    0.85
    fol
    0.85
    mith
    0.84
    hip
    0.83
    Activations Density 0.350%

    No Known Activations