© 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. 17587
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational and procedural compliance

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their usage within sentences

    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
    uta
    -0.66
     Zeal
    -0.64
    itol
    -0.58
     kitten
    -0.58
    thia
    -0.57
    ulla
    -0.56
    ãģł
    -0.56
     GG
    -0.55
    types
    -0.55
     sleeve
    -0.55
    POSITIVE LOGITS
     according
    1.37
     says
    1.15
     said
    1.10
    according
    1.03
     writes
    0.91
     experts
    0.91
    said
    0.87
     analysts
    0.87
     observes
    0.85
     explained
    0.84
    Activations Density 0.791%

    No Known Activations