© 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. 1-RES-JB
    11. 20389
    Prev
    Next
    INDEX
    Explanations

    references to issues or situations involving accusations or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "used"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epoch
    -0.78
    pton
    -0.71
     metab
    -0.68
    ohm
    -0.67
     achievable
    -0.66
    arger
    -0.65
    morrow
    -0.63
     batt
    -0.63
     ascent
    -0.62
     bottom
    -0.61
    POSITIVE LOGITS
    used
    1.03
    uses
    0.91
    iously
    0.83
    umn
    0.80
    using
    0.74
    ãĥ¼ãĥĨãĤ£
    0.74
    fully
    0.74
    adoes
    0.74
     Franch
    0.74
    DOS
    0.70
    Activations Density 0.013%

    No Known Activations