© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 17978
    Prev
    Next
    INDEX
    Explanations

    phrases related to the time period of "offseason"

    oai_token-act-pair · gpt-3.5-turbo

    references to the offseason in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordering
    -0.79
    eq
    -0.78
    enth
    -0.76
    Dat
    -0.73
    attr
    -0.72
    ucle
    -0.71
    ess
    -0.70
    ename
    -0.70
    Jenn
    -0.70
    earchers
    -0.70
    POSITIVE LOGITS
     offseason
    1.07
     roundup
    0.79
     kickoff
    0.72
     infield
    0.69
     breeze
    0.69
     biome
    0.68
     mornings
    0.67
     workouts
    0.67
    ãĥ£
    0.67
     wardrobe
    0.66
    Activations Density 0.006%

    No Known Activations