© 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. 23354
    Prev
    Next
    INDEX
    Explanations

    references to the word "Viridian."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific company or brand name

    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
     Duff
    -0.96
     Anchorage
    -0.93
     Clarkson
    -0.82
     [&
    -0.81
    fo
    -0.78
     Choi
    -0.77
    orney
    -0.71
    loe
    -0.70
    stanbul
    -0.70
     Porter
    -0.70
    POSITIVE LOGITS
     Vir
    2.50
     vir
    2.16
    vir
    1.54
     Gir
    1.53
     Hir
    1.09
     Dak
    1.04
     Petr
    1.04
    virt
    1.03
     bios
    1.01
     Tyr
    1.01
    Activations Density 0.056%

    No Known Activations