© 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. 3-RES-JB
    11. 13668
    Prev
    Next
    INDEX
    Explanations

    words related to actions that involve saving or avoiding something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "save."

    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
    ween
    -0.74
    TY
    -0.73
    present
    -0.66
    âĸ¬
    -0.64
    NK
    -0.63
    ä¹ĭ
    -0.62
     reversal
    -0.61
    orio
    -0.60
     WATCHED
    -0.59
    course
    -0.59
    POSITIVE LOGITS
    nesday
    0.79
    igree
    0.76
    ajor
    0.76
    aved
    0.74
    llan
    0.73
    onda
    0.73
    ashing
    0.72
    grass
    0.71
    illance
    0.70
    veyard
    0.69
    Activations Density 0.009%

    No Known Activations