© 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. 9-RES-JB
    11. 13692
    Prev
    Next
    INDEX
    Explanations

    words related to names, particularly those starting with the letters 'St' and including the letter 'a'

    oai_token-act-pair · gpt-3.5-turbo

    names and phrases that include the syllables "St" and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.66
    Ö¼
    -0.60
    riend
    -0.58
     Haku
    -0.56
    vernment
    -0.56
     Immortal
    -0.55
    rehend
    -0.55
    =-=-=-=-=-=-=-=-
    -0.54
     DRAG
    -0.54
     UFO
    -0.53
    POSITIVE LOGITS
    helm
    1.02
    wart
    0.91
    wagen
    0.88
    leck
    0.87
    warts
    0.85
    gered
    0.85
    ggle
    0.81
    wick
    0.80
    adder
    0.78
    emate
    0.76
    Activations Density 0.146%

    No Known Activations