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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 21915
    Prev
    Next
    INDEX
    Explanations

    scenarios or hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "scenario" and its variations, indicating discussions about hypothetical situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighters
    -0.90
    igion
    -0.83
    alties
    -0.82
    ighter
    -0.82
    ence
    -0.81
    azar
    -0.80
    under
    -0.80
    itsch
    -0.80
    ixed
    -0.79
    ove
    -0.78
    POSITIVE LOGITS
     scenarios
    1.23
     scenario
    1.17
     2030
    0.80
    eers
    0.76
     2050
    0.75
    -+-+
    0.75
     2100
    0.74
     probabilities
    0.70
     simulations
    0.70
    ãĤ¼ãĤ¦ãĤ¹
    0.67
    Activations Density 0.006%

    No Known Activations