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. 19706
    Prev
    Next
    INDEX
    Explanations

    phrases related to depth in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to depth 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
     unpublished
    -0.80
    published
    -0.78
    netflix
    -0.71
    laughs
    -0.71
     Edited
    -0.68
     Lifetime
    -0.67
     published
    -0.63
     Esther
    -0.62
    ride
    -0.62
    eln
    -0.62
    POSITIVE LOGITS
     offensively
    1.25
     duo
    1.12
     scorer
    1.09
     defensively
    1.08
     tandem
    1.06
     defenseman
    1.05
     outfield
    1.04
     winger
    1.01
     midfield
    0.99
     lineback
    0.99
    Activations Density 0.196%

    No Known Activations