Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10700
    Prev
    Next
    INDEX
    Explanations

    gender-related terms and discuss social issues

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the pronoun "He."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Offline
    -0.64
     Toast
    -0.61
     Hive
    -0.61
     Lyme
    -0.61
     Wizards
    -0.60
     Keeper
    -0.59
     Scandinavian
    -0.58
    Reviewer
    -0.55
     Scandinav
    -0.55
     remission
    -0.55
    POSITIVE LOGITS
    zbollah
    1.57
     added
    1.20
     likened
    1.20
    idi
    1.17
     urged
    1.14
     cautioned
    1.13
     cited
    1.11
     blamed
    1.10
     contrasted
    1.10
    pherd
    1.09
    Activations Density 0.117%

    No Known Activations