© 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. 22002
    Prev
    Next
    INDEX
    Explanations

    terms related to specific criteria being met

    oai_token-act-pair · gpt-3.5-turbo

    references to specific criteria or standards

    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
    orld
    -0.79
    joy
    -0.73
    resent
    -0.68
    ership
    -0.67
    ston
    -0.66
    irth
    -0.65
    lar
    -0.63
    lique
    -0.63
    hand
    -0.62
    leases
    -0.62
    POSITIVE LOGITS
     criteria
    1.32
     criterion
    1.01
    erion
    1.00
    witz
    0.81
     thresholds
    0.78
    DragonMagazine
    0.77
     definitions
    0.77
     reviewers
    0.77
     cutoff
    0.75
     dictates
    0.73
    Activations Density 0.015%

    No Known Activations