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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 1187
    Prev
    Next
    INDEX
    Explanations

    phrases related to the arrival or appearance of individuals at a location

    oai_token-act-pair · gpt-3.5-turbo

    instances of characters arriving or approaching in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.78
    phabet
    -0.70
    RT
    -0.68
     hinges
    -0.66
     reliance
    -0.65
    ukong
    -0.64
     breadth
    -0.63
    CENT
    -0.62
    ãģ®é
    -0.62
    prus
    -0.61
    POSITIVE LOGITS
     beside
    0.99
     overhead
    0.95
     nearby
    0.94
     demanding
    0.91
     knocking
    0.89
     asking
    0.88
     intervene
    0.86
     downstairs
    0.85
     intervening
    0.84
     yelling
    0.83
    Activations Density 0.198%

    No Known Activations