© 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. 0-RES-JB
    11. 11286
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names

    oai_token-act-pair · gpt-3.5-turbo

    the letter "l"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aside
    -0.58
     separately
    -0.57
     resultant
    -0.55
     untreated
    -0.54
     subtract
    -0.54
     toss
    -0.54
     compulsory
    -0.54
     compromises
    -0.53
     Paraly
    -0.53
     bare
    -0.53
    POSITIVE LOGITS
    l
    3.63
    lc
    1.98
    ls
    1.95
    lia
    1.84
    lay
    1.81
    lus
    1.77
    lov
    1.77
    los
    1.77
    lio
    1.75
    lik
    1.63
    Activations Density 0.031%

    No Known Activations