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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13099
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Her"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character named "Her"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ————
    -0.77
    ype
    -0.76
    ozy
    -0.74
    ypes
    -0.74
    inctions
    -0.69
    eering
    -0.69
    ornia
    -0.69
    anamo
    -0.69
    yip
    -0.67
    VERTIS
    -0.65
    POSITIVE LOGITS
    itage
    1.44
     Majesty
    1.36
    metic
    1.15
    ding
    1.10
    itability
    1.05
    acl
    1.05
    cule
    1.04
    self
    0.97
    mits
    0.97
    mit
    0.96
    Activations Density 0.064%

    No Known Activations