© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5547
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find specific triggering words that indicate the start of a new section or topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of conversational or narrative transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mate
    -0.63
     commun
    -0.62
     ',
    -0.60
     transc
    -0.60
     '.
    -0.59
     lit
    -0.57
     ILCS
    -0.55
     VIDE
    -0.55
     virgin
    -0.54
     cutter
    -0.54
    POSITIVE LOGITS
    Else
    0.83
    :(
    0.76
    hesda
    0.75
    mosp
    0.73
    APS
    0.72
    Weak
    0.71
    Jew
    0.67
    Pr
    0.66
    agar
    0.66
    auga
    0.66
    Activations Density 0.147%

    No Known Activations