© 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. 24467
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptions indicating quality or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    positive or negative evaluations

    oai_token-act-pair · gpt-3.5-turbo
    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
    roots
    -0.53
    doms
    -0.52
     VIDEOS
    -0.52
    merce
    -0.51
    insula
    -0.50
    ipeg
    -0.49
    rouse
    -0.48
     livest
    -0.48
     administrations
    -0.47
    Previous
    -0.47
    POSITIVE LOGITS
    urated
    0.69
    enced
    0.57
    uable
    0.57
    omorphic
    0.55
    actly
    0.55
    cerned
    0.54
     enough
    0.53
    uble
    0.52
     Beir
    0.52
     Ichigo
    0.52
    Activations Density 1.692%

    No Known Activations