© 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. 9-RES-JB
    11. 15679
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to meetings or receptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "met."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slic
    -0.68
     tentacles
    -0.62
     floats
    -0.62
     commentary
    -0.62
     positioning
    -0.56
     foreground
    -0.56
     slices
    -0.56
     iod
    -0.55
     advant
    -0.55
     cone
    -0.54
    POSITIVE LOGITS
    amorph
    1.45
    ropolis
    1.22
    tle
    1.14
    ered
    1.10
    agame
    1.08
    atars
    1.01
    onym
    0.98
    rose
    0.97
    ioned
    0.94
    rior
    0.91
    Activations Density 0.026%

    No Known Activations