© 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. 3-RES-JB
    11. 21260
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing or experiencing pressure, constraint, or obstruction

    oai_token-act-pair · gpt-3.5-turbo

    words related to location and proximity

    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
    oys
    -0.76
    orah
    -0.72
    arat
    -0.66
     dressing
    -0.65
     bund
    -0.64
    mar
    -0.64
    woods
    -0.64
    den
    -0.64
    character
    -0.60
     repaid
    -0.60
    POSITIVE LOGITS
     ILCS
    0.84
     Franch
    0.82
    ptives
    0.77
    milo
    0.75
    chnology
    0.72
    asy
    0.71
    figure
    0.71
    tsky
    0.70
    atives
    0.69
    urally
    0.67
    Activations Density 0.041%

    No Known Activations