© 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. 4-RES-JB
    11. 7280
    Prev
    Next
    INDEX
    Explanations

    words related to sports, particularly golfing and surfing

    oai_token-act-pair · gpt-3.5-turbo

    words related to sports, particularly those involving water and skiing activities

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

    No Comments

    Negative Logits
    ories
    -0.70
    External
    -0.63
     vacant
    -0.62
    Capital
    -0.61
    ADRA
    -0.60
     Treasury
    -0.60
    itutional
    -0.60
     shutdown
    -0.59
     reinvest
    -0.59
     Territories
    -0.59
    POSITIVE LOGITS
    esses
    0.84
     extraord
    0.82
    culosis
    0.72
    ess
    0.69
     beware
    0.68
    inic
    0.68
     derby
    0.67
    pedia
    0.67
     who
    0.66
    maid
    0.65
    Activations Density 0.109%

    No Known Activations