© 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. 3-RES-JB
    11. 8281
    Prev
    Next
    INDEX
    Explanations

    references to numbers or numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or entities denoted by numbers, particularly in a thematic or narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.78
    raised
    -0.69
    USD
    -0.69
    ulating
    -0.68
    IRC
    -0.68
    inventoryQuantity
    -0.66
    Downloadha
    -0.66
    uterte
    -0.66
    oldemort
    -0.65
    activity
    -0.65
    POSITIVE LOGITS
    teen
    1.15
     Mile
    0.94
     Cities
    0.89
     Seasons
    0.88
     Lives
    0.88
     Hundred
    0.86
     Eye
    0.85
     Siege
    0.84
     Eight
    0.83
     Island
    0.83
    Activations Density 0.022%

    No Known Activations