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. 11-RES-JB
    6. 19000
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitions and political events

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with competitive events and contests

    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
    asus
    -0.63
     accessory
    -0.62
     intoxication
    -0.62
    arde
    -0.61
     deficiency
    -0.58
     alteration
    -0.58
     foundation
    -0.56
    brain
    -0.55
    bal
    -0.55
    less
    -0.55
    POSITIVE LOGITS
    hips
    1.34
    hare
    1.27
    hip
    1.23
    hops
    1.21
    cale
    1.13
    creen
    1.13
    manship
    1.11
    poons
    1.02
    paces
    1.01
    etting
    1.00
    Activations Density 0.310%

    No Known Activations