© 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. 8-RES-JB
    11. 19391
    Prev
    Next
    INDEX
    Explanations

    actions or events that occur after a specific time or incident

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with the word "After."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.72
    NRS
    -0.71
    IZE
    -0.70
    Especially
    -0.67
    JV
    -0.66
     constitu
    -0.64
    uci
    -0.63
    DN
    -0.63
    âģ
    -0.62
     unfocusedRange
    -0.61
    POSITIVE LOGITS
    wards
    1.36
    noon
    1.34
    ward
    1.31
    math
    1.24
    words
    1.08
    word
    0.98
     graduating
    0.94
     completing
    0.91
     reviewing
    0.91
     awhile
    0.90
    Activations Density 0.066%

    No Known Activations