© 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. 20656
    Prev
    Next
    INDEX
    Explanations

    words related to qualifiers or identifiers, especially in the context of sports or technology

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to classification and identification

    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
    arnaev
    -0.74
    hire
    -0.74
    irez
    -0.72
     reconc
    -0.69
    sal
    -0.69
    roll
    -0.69
    edo
    -0.68
    ez
    -0.66
    rote
    -0.66
    esh
    -0.65
    POSITIVE LOGITS
    ifiers
    0.97
    ifier
    0.94
    ãĤ§
    0.82
    Reviewer
    0.80
    ãĥ¤
    0.71
    gex
    0.71
    gence
    0.70
    okia
    0.69
    naissance
    0.66
    ference
    0.66
    Activations Density 0.024%

    No Known Activations