© 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. 10-RES-JB
    11. 12895
    Prev
    Next
    INDEX
    Explanations

    terms related to the pitching of an idea or a product

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pitch"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iliary
    -0.87
    hips
    -0.81
    liness
    -0.75
    uous
    -0.72
    tesy
    -0.70
    uala
    -0.69
    ively
    -0.64
    avis
    -0.63
    ual
    -0.63
     captcha
    -0.61
    POSITIVE LOGITS
    fork
    1.47
     pitched
    0.80
     pitches
    0.73
     tents
    0.73
     pitch
    0.73
    veyard
    0.73
    casters
    0.71
    idon
    0.71
     Zar
    0.71
    for
    0.69
    Activations Density 0.032%

    No Known Activations