© 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. 8-RES-JB
    11. 6506
    Prev
    Next
    INDEX
    Explanations

    statistics or facts related to gender disparities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "are" in various contexts related to gender and inequality issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xxxxxxxx
    -0.72
    ulence
    -0.71
     Telesc
    -0.69
    inventoryQuantity
    -0.68
    worthiness
    -0.66
    bye
    -0.65
    osate
    -0.64
    iversary
    -0.64
     transpired
    -0.63
     signifies
    -0.62
    POSITIVE LOGITS
     accustomed
    1.11
     reluctant
    1.10
     aware
    1.07
     willing
    1.04
     eager
    1.04
     able
    1.00
     afraid
    1.00
     encouraged
    1.00
     unable
    0.99
     happiest
    0.98
    Activations Density 0.285%

    No Known Activations