© 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. 3168
    Prev
    Next
    INDEX
    Explanations

    mentions of the phrase "Handmaid's Tale"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Hand" in various contexts

    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
    iries
    -0.68
    autical
    -0.67
     RAND
    -0.64
    AIR
    -0.63
    uses
    -0.63
    rd
    -0.63
    ITAL
    -0.62
     Mercer
    -0.61
     Amtrak
    -0.60
     Weir
    -0.60
    POSITIVE LOGITS
    maid
    1.11
     Hand
    1.05
    shake
    1.01
    eln
    0.90
    hander
    0.89
    Hand
    0.88
    legate
    0.87
    hand
    0.87
    axe
    0.82
    lers
    0.81
    Activations Density 0.006%

    No Known Activations