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. 8123
    Prev
    Next
    INDEX
    Explanations

    keywords related to past statistics or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference recent seasons or time periods in sports contexts

    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
    oola
    -0.83
    aband
    -0.74
    cil
    -0.72
    ansk
    -0.70
    erning
    -0.68
    ilateral
    -0.68
    kaya
    -0.67
    rite
    -0.67
    obs
    -0.67
    ordes
    -0.65
    POSITIVE LOGITS
     ditch
    1.04
     week
    0.98
     month
    0.93
     year
    0.91
     season
    0.87
     minute
    0.85
     semester
    0.78
     decade
    0.78
     outing
    0.78
     night
    0.77
    Activations Density 0.061%

    No Known Activations