© 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. 16011
    Prev
    Next
    INDEX
    Explanations

    references to financial terms related to investments and legal statuses like citizens, slaves, and contractors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles and identities within society

    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
    etus
    -0.64
    atorium
    -0.62
    forestation
    -0.61
     Volcano
    -0.59
     Vortex
    -0.59
    aminer
    -0.59
     Boom
    -0.59
    osion
    -0.58
    osphere
    -0.58
     insanity
    -0.58
    POSITIVE LOGITS
     themselves
    1.24
    hips
    1.11
     respectively
    0.97
     ourselves
    0.97
    pots
    0.93
    paces
    0.93
    uits
    0.93
     unto
    0.90
    avers
    0.89
    umers
    0.86
    Activations Density 0.197%

    No Known Activations