Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 7837
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative situations or potential dangers

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to urgent issues or crises that require attention

    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
    aeus
    -0.82
    ocry
    -0.80
    ahon
    -0.79
    Aff
    -0.74
    ramid
    -0.74
    Yep
    -0.73
    hemy
    -0.70
    ramids
    -0.69
    istine
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.68
    POSITIVE LOGITS
     urgently
    0.96
     urgent
    0.96
     urgency
    0.96
     policymakers
    0.90
     needs
    0.89
    Solution
    0.89
     Governments
    0.85
     need
    0.84
     evac
    0.83
     Ministers
    0.81
    Activations Density 0.694%

    No Known Activations