© 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. 4-RES-JB
    11. 4838
    Prev
    Next
    INDEX
    Explanations

    questions related to a specific topic or action

    oai_token-act-pair · gpt-3.5-turbo

    questions or phrases beginning with "where" or similar structures

    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
    telling
    -0.64
     Fargo
    -0.63
    ãĤ¹ãĥĪ
    -0.62
    pine
    -0.62
     1954
    -0.57
    kamp
    -0.56
     Organization
    -0.56
     ANN
    -0.56
     Digest
    -0.56
     Franco
    -0.55
    POSITIVE LOGITS
    abouts
    0.75
    quickShipAvailable
    0.69
     nearest
    0.67
    eneg
    0.67
     boarded
    0.66
     clicked
    0.66
     awaited
    0.66
    'd
    0.64
     attacked
    0.64
     messed
    0.63
    Activations Density 0.159%

    No Known Activations