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. 24016
    Prev
    Next
    INDEX
    Explanations

    references to the legality or illegality of various activities or substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the legality of marijuana

    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
    ortment
    -0.71
    PsyNetMessage
    -0.65
    ortun
    -0.63
    Reb
    -0.62
    aida
    -0.62
    ravings
    -0.61
    aleb
    -0.61
    ILA
    -0.61
    quart
    -0.60
     Advent
    -0.60
    POSITIVE LOGITS
     enough
    0.97
    isable
    0.86
    izable
    0.85
    aneously
    0.81
     anyway
    0.79
     unless
    0.78
     anymore
    0.77
    .''
    0.73
     ashore
    0.72
     Ichigo
    0.72
    Activations Density 0.295%

    No Known Activations