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. 15920
    Prev
    Next
    INDEX
    Explanations

    references to specific sports teams or players

    oai_token-act-pair · gpt-3.5-turbo

    references to the football club Fulham and associated players

    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
    shapeshifter
    -0.90
     Miko
    -0.89
    Dialogue
    -0.74
    ++++++++++++++++
    -0.74
     Metatron
    -0.72
     Gamble
    -0.70
     Collector
    -0.69
     Visitors
    -0.69
    anwhile
    -0.68
    Reward
    -0.67
    POSITIVE LOGITS
    vous
    0.96
    gur
    0.96
    isine
    0.93
    rique
    0.93
    grim
    0.90
    rican
    0.87
    ighters
    0.87
    ife
    0.87
    gent
    0.85
    aces
    0.85
    Activations Density 0.020%

    No Known Activations