© 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. 8-RES-JB
    11. 12351
    Prev
    Next
    INDEX
    Explanations

    references to significant changes or transformations over time

    oai_token-act-pair · gpt-3.5-turbo

    references to change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mination
    -0.77
    stra
    -0.63
    amina
    -0.62
    çĦ
    -0.61
    isy
    -0.60
    vern
    -0.60
    ç«
    -0.60
    ci
    -0.59
     Ys
    -0.59
    Assembly
    -0.58
    POSITIVE LOGITS
     drastically
    1.01
     dramatically
    0.99
     radically
    0.86
    ĸļ
    0.84
     abruptly
    0.84
     materially
    0.80
    amorph
    0.80
    iating
    0.79
     markedly
    0.78
    ulet
    0.75
    Activations Density 0.058%

    No Known Activations