© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6430
    Prev
    Next
    INDEX
    Explanations

    special characters such as symbols, accents, and punctuation

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viron
    -0.85
    vern
    -0.76
    ciating
    -0.76
    ctions
    -0.76
    nings
    -0.75
    keepers
    -0.75
    nces
    -0.74
    cius
    -0.74
    gers
    -0.73
    selage
    -0.72
    POSITIVE LOGITS
    ÑĮ
    0.90
    »
    0.90
    ħ
    0.86
    issions
    0.84
    âĶģ
    0.76
    åĭ
    0.75
    ãĥĺ
    0.75
    º
    0.71
    alk
    0.71
    ç¥ŀ
    0.71
    Activations Density 0.004%

    No Known Activations