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. 3-RES-JB
    6. 955
    Prev
    Next
    INDEX
    Explanations

    references to AK-47 rifles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the AK-47 assault rifle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ£
    -0.77
    ãĤ§
    -0.76
     Vaugh
    -0.74
    nces
    -0.73
     guiActiveUnfocused
    -0.72
     istg
    -0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.71
    advertisement
    -0.70
     Kepler
    -0.70
    issance
    -0.70
    POSITIVE LOGITS
    AZ
    0.82
     AK
    0.80
    istani
    0.79
    atana
    0.79
    AK
    0.74
    iy
    0.72
    unta
    0.72
    ansas
    0.71
    DEN
    0.69
    rew
    0.68
    Activations Density 0.005%

    No Known Activations