© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6081
    Prev
    Next
    INDEX
    Explanations

    references to political executive orders

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rown
    -0.84
    dden
    -0.79
    lehem
    -0.71
     Argon
    -0.71
     Vish
    -0.68
    nia
    -0.67
     Pix
    -0.66
     Cats
    -0.66
    Lost
    -0.65
    ENE
    -0.64
    POSITIVE LOGITS
    BOOK
    0.77
     vetoed
    0.77
     pard
    0.76
    book
    0.75
    urated
    0.75
     helicop
    0.73
     approvals
    0.71
     decree
    0.71
     banning
    0.70
     legalizing
    0.70
    Activations Density 0.045%

    No Known Activations