© 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. 2-RES-JB
    11. 18898
    Prev
    Next
    INDEX
    Explanations

    statements or actions indicating decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decided" indicating choices or decisions being made

    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
    ikan
    -0.72
    resa
    -0.70
    atha
    -0.67
    clad
    -0.67
    ciating
    -0.65
    alle
    -0.65
    amina
    -0.63
    heed
    -0.63
    ggies
    -0.63
    eah
    -0.63
    POSITIVE LOGITS
     decides
    0.87
     decided
    0.85
     Garc
    0.82
     decide
    0.78
     unanimously
    0.76
    Ń·
    0.75
     ($)
    0.74
     upon
    0.70
    ãģ®éŃĶ
    0.68
    使
    0.67
    Activations Density 0.035%

    No Known Activations