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. 21691
    Prev
    Next
    INDEX
    Explanations

    locations or events associated with political rallies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" related to events or rallies

    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
    omers
    -0.74
    CLASSIFIED
    -0.74
    username
    -0.73
    hirt
    -0.70
     learners
    -0.70
     engineers
    -0.70
    ibur
    -0.70
    ensor
    -0.68
    NOW
    -0.68
    ¿½
    -0.67
    POSITIVE LOGITS
     conjunction
    1.34
     lieu
    1.24
     favor
    1.06
     commem
    1.03
     accordance
    1.03
     vitro
    1.03
     unison
    0.99
     Charlottesville
    0.95
     France
    0.94
    roads
    0.93
    Activations Density 0.432%

    No Known Activations