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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 6893
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific football players

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rodgers" in various contexts, particularly in relation to sports

    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
    uate
    -1.01
    uates
    -0.89
    uated
    -0.84
    izations
    -0.77
    aneously
    -0.76
    uating
    -0.74
    WHERE
    -0.67
     horizon
    -0.66
     justices
    -0.66
    eneg
    -0.66
    POSITIVE LOGITS
     Rodgers
    0.98
    manship
    0.90
    gers
    0.80
    mith
    0.79
    etta
    0.78
    cano
    0.77
    bey
    0.76
    adier
    0.75
    sey
    0.74
    cliffe
    0.73
    Activations Density 0.015%

    No Known Activations