© 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. 7-RES-JB
    11. 12629
    Prev
    Next
    INDEX
    Explanations

    professional titles and roles

    oai_token-act-pair · gpt-3.5-turbo

    references to significant individuals or professionals with influence or expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regress
    -0.70
    rates
    -0.69
    ilib
    -0.67
    orders
    -0.67
    tten
    -0.64
    igans
    -0.60
    atives
    -0.60
    chers
    -0.60
    udicrous
    -0.60
    nuts
    -0.59
    POSITIVE LOGITS
     preferably
    1.12
     or
    1.06
    cknow
    1.01
     spouse
    0.94
     optionally
    0.81
    either
    0.78
     either
    0.76
    specified
    0.75
    typically
    0.75
    ichever
    0.73
    Activations Density 1.129%

    No Known Activations