© 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. 9-RES-JB
    11. 15393
    Prev
    Next
    INDEX
    Explanations

    phrases related to a period leading up to an event or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related concepts and the idea of progression or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paio
    -0.66
     Parties
    -0.60
    anie
    -0.60
     Converted
    -0.59
    ottage
    -0.58
     Instit
    -0.57
     Shows
    -0.57
    arag
    -0.52
     Burk
    -0.50
     Yorkers
    -0.50
    POSITIVE LOGITS
    osphere
    0.81
    ixties
    0.76
    DragonMagazine
    0.75
    soDeliveryDate
    0.71
    rium
    0.70
    iest
    0.69
     hierarchy
    0.69
     sciences
    0.69
     aisle
    0.68
    Sphere
    0.67
    Activations Density 0.388%

    No Known Activations