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. 4-RES-JB
    6. 5432
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender, political parties, and sports teams

    oai_token-act-pair · gpt-3.5-turbo

    references to gender and political groups

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

    No Comments

    Negative Logits
     Newsletter
    -0.73
     Collider
    -0.64
     Recommend
    -0.61
     dehyd
    -0.60
     Parables
    -0.59
     Cavern
    -0.57
     backlog
    -0.57
    odcast
    -0.56
     Asc
    -0.55
     Altern
    -0.54
    POSITIVE LOGITS
     sexes
    1.21
     sides
    0.90
     halves
    0.83
     equally
    0.83
     genders
    0.81
    ieth
    0.80
     simultaneously
    0.80
    aughed
    0.75
    paces
    0.75
     extremes
    0.70
    Activations Density 0.120%

    No Known Activations