© 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. 10-RES-JB
    11. 20627
    Prev
    Next
    INDEX
    Explanations

    words related to complex mental processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the mind and mental states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atar
    -0.83
    isoft
    -0.71
    iability
    -0.67
     Suc
    -0.63
    orah
    -0.62
     Coverage
    -0.61
     Grounds
    -0.61
     exclude
    -0.61
    acco
    -0.60
    acebook
    -0.60
    POSITIVE LOGITS
    umbing
    0.87
    ogg
    0.86
    bending
    0.82
    ãĤ´ãĥ³
    0.79
     shattering
    0.76
    consuming
    0.75
    machine
    0.72
    felt
    0.72
     numb
    0.71
    oeuv
    0.71
    Activations Density 0.074%

    No Known Activations