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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 9466
    Prev
    Next
    INDEX
    Explanations

    references to gender identity and related topics like restrooms, facilities, and locker rooms

    oai_token-act-pair · gpt-3.5-turbo

    references to gender identity and related policies

    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
     thunder
    -0.73
     Byr
    -0.69
    uncture
    -0.67
     Exc
    -0.67
     Winc
    -0.66
    baugh
    -0.66
     Prices
    -0.65
    Money
    -0.65
    UF
    -0.64
     Ley
    -0.63
    POSITIVE LOGITS
    iannopoulos
    0.88
     pronouns
    0.84
     disorder
    0.79
    aki
    0.78
     identity
    0.75
     dysph
    0.74
     transitioned
    0.73
     Identity
    0.72
     Disorders
    0.71
    ference
    0.70
    Activations Density 0.091%

    No Known Activations