© 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. 0-RES-JB
    11. 16577
    Prev
    Next
    INDEX
    Explanations

    dates in the format of day-month-year

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "22."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    ief
    -0.65
     destro
    -0.63
     seiz
    -0.62
     rul
    -0.61
    soType
    -0.59
    zos
    -0.59
     behavi
    -0.57
    za
    -0.57
    inventoryQuantity
    -0.57
    ocus
    -0.56
    POSITIVE LOGITS
     22
    2.85
     23
    2.28
     21
    2.28
     26
    2.11
     28
    2.10
     42
    1.96
     19
    1.95
     27
    1.94
     29
    1.93
     24
    1.90
    Activations Density 0.040%

    No Known Activations