© 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 EvalsExportsinterp-engineNEWAPI 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. 18548
    Prev
    Next
    INDEX
    Explanations

    additional information or elements being added to a description or list

    oai_token-act-pair · gpt-3.5-turbo

    references to supplementary information or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    irin
    -0.70
    risome
    -0.69
    bane
    -0.67
    utters
    -0.65
    baby
    -0.64
    jam
    -0.64
    boys
    -0.62
     jelly
    -0.60
     cust
    -0.58
    anus
    -0.58
    POSITIVE LOGITS
    olkien
    0.91
     Osw
    0.81
     guiActiveUn
    0.70
    tions
    0.67
    Murray
    0.66
    hesis
    0.65
     parentheses
    0.65
    ãĤ½
    0.63
     thereto
    0.63
    nyder
    0.62
    Activations Density 0.017%

    No Known Activations