© 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. 3-RES-JB
    11. 19539
    Prev
    Next
    INDEX
    Explanations

    precise or final answers to queries or statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "definitive" or its variations

    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
    hire
    -0.75
    awar
    -0.75
    light
    -0.72
    enium
    -0.72
    nan
    -0.72
    ÃŁ
    -0.70
    ĺħ
    -0.70
    cock
    -0.68
    ħ
    -0.68
    ulton
    -0.68
    POSITIVE LOGITS
     definitive
    0.93
     indication
    0.79
    aneously
    0.76
     conclusive
    0.75
    itatively
    0.75
    answer
    0.74
     Definitive
    0.73
     rethink
    0.72
     answer
    0.72
     FORM
    0.68
    Activations Density 0.018%

    No Known Activations