© 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. 7-RES-JB
    11. 20832
    Prev
    Next
    INDEX
    Explanations

    When the neuron fires, it looks for the word "indeed" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "indeed" and its variations to emphasize certainty or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rals
    -0.63
    Streamer
    -0.61
    76561
    -0.59
    Mesh
    -0.59
    center
    -0.58
    assic
    -0.57
    Winged
    -0.57
    Ĺ
    -0.56
    QB
    -0.56
     weap
    -0.56
    POSITIVE LOGITS
    ional
    0.88
    uala
    0.79
     qualifies
    0.72
    EngineDebug
    0.68
     belong
    0.66
    arist
    0.65
    netflix
    0.64
    eem
    0.64
     formatted
    0.64
    forth
    0.63
    Activations Density 0.017%

    No Known Activations