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. 12617
    Prev
    Next
    INDEX
    Explanations

    mentions of elections and political events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to electoral processes or voting

    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
     Sparrow
    -0.72
     Falk
    -0.72
     Reloaded
    -0.68
     Stronghold
    -0.68
     explanatory
    -0.65
     Dur
    -0.63
     Crescent
    -0.62
     Continental
    -0.60
     Chambers
    -0.60
     Dominican
    -0.59
    POSITIVE LOGITS
    profit
    1.02
    minded
    1.01
    profits
    0.99
    morrow
    0.97
    yet
    0.92
    reply
    0.92
    duty
    0.91
    sided
    0.90
    risk
    0.90
    rans
    0.89
    Activations Density 0.049%

    No Known Activations