© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 24409
    Prev
    Next
    INDEX
    Explanations

    keywords related to statistics and prevalence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the frequency or rate of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -1.01
    iverse
    -0.91
    erm
    -0.84
    shaw
    -0.80
    wagen
    -0.77
    imb
    -0.75
    ilver
    -0.72
    hatt
    -0.71
    onde
    -0.70
    orld
    -0.70
    POSITIVE LOGITS
     prevalence
    1.01
     occurrence
    0.95
     preval
    0.95
     rates
    0.88
     incidence
    0.87
     (%)
    0.77
     rate
    0.77
     variability
    0.76
    errors
    0.76
     occurrences
    0.74
    Activations Density 0.020%

    No Known Activations