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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1141
    Prev
    Next
    INDEX
    Explanations

    specific document structure elements, perhaps related to code or formatting, marked by special characters

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or performance metrics related to sports players and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solic
    -0.78
    heit
    -0.77
     ______
    -0.76
    awei
    -0.75
    igslist
    -0.74
    illance
    -0.71
     ACS
    -0.70
     Cindy
    -0.69
    Ń·
    -0.69
     purs
    -0.65
    POSITIVE LOGITS
    England
    0.94
    Players
    0.92
    Liverpool
    0.91
    Sport
    0.84
    Football
    0.84
    Coach
    0.81
    sports
    0.78
    Speaking
    0.77
    Having
    0.77
    Scotland
    0.76
    Activations Density 0.305%

    No Known Activations