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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 9700
    Prev
    Next
    INDEX
    Explanations

    references to a specific place or organization named "Gard" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Gard" and its variations, indicating a focus on law enforcement or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AMA
    -0.65
     Vice
    -0.62
     Oslo
    -0.58
    ting
    -0.57
     favoring
    -0.56
     VP
    -0.55
     vice
    -0.54
     Butt
    -0.54
     Musk
    -0.54
     Omaha
    -0.53
    POSITIVE LOGITS
    ener
    1.29
    aret
    1.06
    ening
    1.04
    endale
    1.04
    apons
    0.99
    iner
    0.99
    yne
    0.94
    llan
    0.92
    arden
    0.89
    inia
    0.88
    Activations Density 0.039%

    No Known Activations