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. 17741
    Prev
    Next
    INDEX
    Explanations

    terms related to sports drafts and selections

    oai_token-act-pair · gpt-3.5-turbo

    references to draft picks in sporting events

    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
    cers
    -0.70
    interrupted
    -0.67
     testim
    -0.65
     Documentation
    -0.65
    isf
    -0.64
    Compl
    -0.63
    MpServer
    -0.63
     millenn
    -0.63
    bara
    -0.61
     tempor
    -0.60
    POSITIVE LOGITS
     (#
    0.96
     picks
    0.84
     lottery
    0.83
     compens
    0.83
     slot
    0.80
    pocket
    0.79
     Picks
    0.76
     overall
    0.75
     coveted
    0.73
     acquired
    0.73
    Activations Density 0.039%

    No Known Activations