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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 21826
    Prev
    Next
    INDEX
    Explanations

    URLs or website links

    oai_token-act-pair · gpt-3.5-turbo

    letters or characters in a string of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BART
    -0.78
    ERY
    -0.76
    ICAL
    -0.73
    NESS
    -0.71
    ħĭ
    -0.71
    LEY
    -0.69
    ĪĴ
    -0.68
    heimer
    -0.67
     Awakens
    -0.64
     Conditions
    -0.63
    POSITIVE LOGITS
    eatured
    1.06
    cd
    1.05
    cs
    1.05
    orthern
    1.02
    irgin
    0.99
    ynamic
    0.98
    fs
    0.98
    jac
    0.97
    redits
    0.97
    ickets
    0.96
    Activations Density 0.097%

    No Known Activations