© 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. 7-RES-JB
    11. 13443
    Prev
    Next
    INDEX
    Explanations

    instances where the text discusses a numerical quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a large number or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quote
    -0.77
    âĺ
    -0.70
    interstitial
    -0.67
    DragonMagazine
    -0.64
    cause
    -0.63
    SF
    -0.61
    Tomorrow
    -0.61
    MpServer
    -0.61
    FOR
    -0.60
    Pri
    -0.59
    POSITIVE LOGITS
     years
    0.99
     exhausting
    0.99
     unsuccessful
    0.95
     generations
    0.94
     hiatus
    0.88
     seasons
    0.88
     decades
    0.88
     stint
    0.87
     iterations
    0.87
     periods
    0.87
    Activations Density 0.115%

    No Known Activations