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

    Neuronpedia

    APICircuit 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. 16935
    Prev
    Next
    INDEX
    Explanations

    examples of sentences containing specific locations or positions within a sports context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "at" associated with positions or roles in a sports context

    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
    SPONSORED
    -0.80
    ureen
    -0.74
    ality
    -0.69
    izo
    -0.67
    alities
    -0.67
    ÄŁ
    -0.67
    PET
    -0.67
    usercontent
    -0.67
    ivity
    -0.66
    etti
    -0.65
    POSITIVE LOGITS
     fullback
    1.05
     shortstop
    1.04
     times
    1.00
     halftime
    0.99
     cornerback
    0.98
     quarterback
    0.98
     least
    0.94
     linebacker
    0.91
     QB
    0.91
     age
    0.87
    Activations Density 0.069%

    No Known Activations