© 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. 4-RES-JB
    11. 7111
    Prev
    Next
    INDEX
    Explanations

    words related to political figures or locations

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific names or nouns

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

    No Comments

    Negative Logits
    schild
    -0.67
    recomm
    -0.64
    CLASS
    -0.62
    ovych
    -0.61
     caution
    -0.59
     lamb
    -0.58
     fury
    -0.57
     shine
    -0.57
     upset
    -0.56
     goodwill
    -0.55
    POSITIVE LOGITS
    ulhu
    0.95
    pillar
    0.93
    estine
    0.86
    arette
    0.85
    rera
    0.85
    ãĤ¼ãĤ¦ãĤ¹
    0.83
    berus
    0.83
    illo
    0.80
    inelli
    0.80
    emporary
    0.76
    Activations Density 0.106%

    No Known Activations