© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22452
    Prev
    Next
    INDEX
    Explanations

    direct references to movie titles within text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks

    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
    " token" vs "Token"

    No Comments

    Negative Logits
     grasp
    -0.86
     care
    -0.86
     disciplinary
    -0.80
     matter
    -0.80
     delivery
    -0.80
     grips
    -0.79
     grav
    -0.77
     batter
    -0.77
     outfielder
    -0.77
     methodological
    -0.77
    POSITIVE LOGITS
    Eat
    1.36
    Morning
    1.35
    Operation
    1.30
    Dear
    1.30
    Big
    1.28
    Bad
    1.27
    Friends
    1.26
    Golden
    1.26
    Untitled
    1.25
    Saturday
    1.23
    Activations Density 0.100%

    No Known Activations