© 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. 1-RES-JB
    11. 7658
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name, "Sch"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sch" followed by various numbers or descriptions, indicating a focus on specific individuals or subjects related to that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censored
    -0.80
     constrained
    -0.72
     cens
    -0.68
    Downloadha
    -0.68
     permitting
    -0.68
     commissions
    -0.67
     Korra
    -0.66
    DragonMagazine
    -0.65
    LECT
    -0.65
     permit
    -0.64
    POSITIVE LOGITS
    izoph
    1.28
    acht
    1.13
    izophren
    0.93
    utz
    0.93
    afer
    0.91
    umann
    0.91
    ram
    0.87
    etz
    0.86
    acher
    0.86
    ulz
    0.85
    Activations Density 0.008%

    No Known Activations