Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23353
    Prev
    Next
    INDEX
    Explanations

    locations or places with 'i' as a notable feature

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.75
    cens
    -0.74
    lain
    -0.73
    e
    -0.68
    laus
    -0.67
    t
    -0.67
    tons
    -0.65
    edly
    -0.64
    sed
    -0.64
    s
    -0.62
    POSITIVE LOGITS
    plom
    1.18
    Äĩ
    1.15
    orno
    1.15
    essen
    1.07
    ère
    1.06
    kson
    0.97
    ordan
    0.92
    qa
    0.90
    elson
    0.90
    abetes
    0.90
    Activations Density 0.089%

    No Known Activations