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. 10-RES-JB
    6. 1659
    Prev
    Next
    INDEX
    Explanations

    numerical and alphabetic patterns within specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to announcements and notifications related to various topics

    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
    jet
    -0.81
    fair
    -0.78
    tons
    -0.69
    aug
    -0.67
    plain
    -0.66
    jun
    -0.66
    kell
    -0.66
    fal
    -0.65
    comb
    -0.65
    boy
    -0.65
    POSITIVE LOGITS
    ING
    1.77
    IES
    1.77
    ITY
    1.77
    ABLE
    1.70
    ED
    1.69
    ATIONS
    1.69
    IZ
    1.69
    ION
    1.68
    ATION
    1.66
    ORS
    1.66
    Activations Density 0.146%

    No Known Activations