© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    verbs related to providing information, insights, or explanations

    oai_token-act-pair · gpt-3.5-turbo

    words related to providing information, assurances, or offers

    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
    iazep
    -0.80
     helicop
    -0.73
    luaj
    -0.72
    bill
    -0.67
    è¦ļéĨĴ
    -0.67
     condem
    -0.66
    AH
    -0.65
    shit
    -0.64
    noticed
    -0.64
     tyr
    -0.63
    POSITIVE LOGITS
     us
    0.74
     uniquely
    0.72
     probabilities
    0.71
    ANCE
    0.66
     distinct
    0.65
    ments
    0.64
     intrinsic
    0.64
     clues
    0.63
    ando
    0.63
     inex
    0.62
    Activations Density 0.374%

    No Known Activations