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. 9-RES-JB
    6. 21352
    Prev
    Next
    INDEX
    Explanations

    details related to conversations between specific groups, such as middle-aged children and the elderly

    oai_token-act-pair · gpt-3.5-turbo

    conversations and interactions between different age groups or social demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -1.04
    Âł
    -0.96
     Whilst
    -0.94
    ".[
    -0.89
    Firstly
    -0.86
    !".
    -0.86
    '.
    -0.79
    ?".
    -0.79
    ".
    -0.75
    ´
    -0.74
    POSITIVE LOGITS
     nonprofits
    0.74
    earchers
    0.74
    Newsletter
    0.70
    Enlarge
    0.67
     Southwest
    0.63
     nonprofit
    0.63
    CLOSE
    0.62
     cellphone
    0.61
     Whitman
    0.60
     spokeswoman
    0.59
    Activations Density 2.651%

    No Known Activations