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. 11951
    Prev
    Next
    INDEX
    Explanations

    gender-specific possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to women's categories or events

    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
    mr
    -0.83
    uncle
    -0.79
    hiba
    -0.77
    hari
    -0.75
    Reviewer
    -0.74
    leased
    -0.73
    cedented
    -0.71
    ciating
    -0.70
    ific
    -0.70
    osponsors
    -0.70
    POSITIVE LOGITS
     International
    0.74
     Caucus
    0.74
     Cooper
    0.72
     rights
    0.70
     participation
    0.69
     Liberation
    0.69
     pursuit
    0.68
     clubs
    0.68
     Crusade
    0.68
    istance
    0.66
    Activations Density 0.053%

    No Known Activations