© 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. 8-RES-JB
    11. 7276
    Prev
    Next
    INDEX
    Explanations

    text related to comparisons between different entities or situations

    oai_token-act-pair · gpt-3.5-turbo

    indicators of evident performance or outcomes

    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
    •GPT2 Layer 8 Movie Sentiment Features
    •contextual features
    fires on a <verb> <comparison> like "was evident how" or etc

    No Comments

    Negative Logits
    enegger
    -0.69
    onga
    -0.60
     awa
    -0.60
    eware
    -0.59
    hovah
    -0.58
    onto
    -0.56
     advoc
    -0.55
    erenn
    -0.53
    ÃĥÃĤ
    -0.52
    entimes
    -0.50
    POSITIVE LOGITS
     yesterday
    0.67
     Was
    0.54
     earlier
    0.54
    \":
    0.50
    CVE
    0.50
     Were
    0.50
     ][
    0.49
     pandemonium
    0.49
     evacuated
    0.48
    ãĢIJ
    0.48
    Activations Density 2.255%

    No Known Activations