© 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. 10-RES-JB
    11. 14043
    Prev
    Next
    INDEX
    Explanations

    executive orders or related terms and numbers mentioned in official texts

    oai_token-act-pair · gpt-3.5-turbo

    references to executive orders

    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
    dden
    -0.79
    rose
    -0.75
    kies
    -0.71
    apest
    -0.68
    espie
    -0.67
     Argon
    -0.67
    thought
    -0.66
    allery
    -0.66
    iders
    -0.66
    venture
    -0.65
    POSITIVE LOGITS
     prohibiting
    1.37
     authorizing
    1.31
     forb
    1.21
     issued
    1.19
     directing
    1.19
     banning
    1.19
     restricting
    1.18
     granting
    1.14
     barring
    1.10
     decree
    1.09
    Activations Density 0.119%

    No Known Activations