© 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. 22597
    Prev
    Next
    INDEX
    Explanations

    words related to reactions or responses

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional or physical responses

    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
    locked
    -0.80
    hold
    -0.73
     Sinai
    -0.69
    holder
    -0.68
    iciency
    -0.67
    fusc
    -0.67
     Loaded
    -0.67
    ramer
    -0.65
    enture
    -0.65
     Crimson
    -0.64
    POSITIVE LOGITS
     reaction
    1.23
     reactions
    1.20
    aries
    1.11
    ivation
    1.08
    ivated
    1.04
     Reaction
    1.02
    ivating
    0.98
    naires
    0.87
     thereto
    0.82
    naire
    0.82
    Activations Density 0.015%

    No Known Activations