© 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. 0-RES-JB
    11. 11491
    Prev
    Next
    INDEX
    Explanations

    words related to magic or diseases

    oai_token-act-pair · gpt-3.5-turbo

    words related to "magic" or "magical" themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pub
    -0.73
     hon
    -0.69
     data
    -0.65
     standing
    -0.63
     positions
    -0.62
     cort
    -0.62
     favour
    -0.61
     brow
    -0.61
     polling
    -0.60
     co
    -0.60
    POSITIVE LOGITS
    agic
    4.73
    agy
    1.64
    agos
    1.43
    agically
    1.36
    ago
    1.17
    essage
    1.13
    atic
    1.05
    atical
    1.04
    agin
    1.04
    atically
    1.02
    Activations Density 0.011%

    No Known Activations