© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    phonetic mismatches

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    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
    ©¶æ
    -0.88
     beneficiary
    -0.70
    benef
    -0.68
    figured
    -0.67
     unsuspecting
    -0.64
    pelling
    -0.63
     dart
    -0.63
    ulnerable
    -0.63
     darts
    -0.63
    catch
    -0.63
    POSITIVE LOGITS
    atted
    0.84
    ebook
    0.78
    enez
    0.75
    TN
    0.74
    hetti
    0.73
    auga
    0.73
    ioch
    0.73
    ettes
    0.73
    ione
    0.72
    ICAN
    0.71
    Activations Density 0.018%

    No Known Activations