© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 340
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures and conditions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numeric values in the text

    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
    •Partition Features Layer 8 GPT2 Small

    No Comments

    Negative Logits
     synerg
    -0.96
     orchestr
    -0.88
     migr
    -0.86
     raft
    -0.84
     undet
    -0.83
     coordinated
    -0.82
     displacement
    -0.82
     migration
    -0.82
     frontline
    -0.80
    etheless
    -0.80
    POSITIVE LOGITS
    RAW
    1.51
    Then
    1.42
    Anyway
    1.41
    Advertisement
    1.40
    Question
    1.40
    Reply
    1.40
    Asked
    1.36
    =-=-=-=-=-=-=-=-
    1.34
    Advertisements
    1.33
    Yeah
    1.33
    Activations Density 0.300%

    No Known Activations