© 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. 4-RES-JB
    11. 12439
    Prev
    Next
    INDEX
    Explanations

    The neuron mainly activates on phrases referring to the first thing noticed or recognized in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the first or last significant items in a context

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

    No Comments

    Negative Logits
    inav
    -0.80
    dor
    -0.65
    sted
    -0.64
     anonymity
    -0.64
    åī
    -0.61
     Flavoring
    -0.61
    velop
    -0.60
    76561
    -0.60
    gars
    -0.60
    ipel
    -0.59
    POSITIVE LOGITS
     Valiant
    0.86
     imaginable
    0.82
     happening
    0.79
     happened
    0.78
     happens
    0.78
    ${
    0.77
    iverse
    0.76
     happ
    0.76
    oggle
    0.73
     else
    0.73
    Activations Density 0.022%

    No Known Activations