© 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. 6-RES-JB
    11. 17037
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and its surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plunge
    -0.74
     cut
    -0.67
     entirely
    -0.67
     div
    -0.63
     inappropriately
    -0.62
     equival
    -0.62
     swe
    -0.62
     ability
    -0.61
     blocker
    -0.61
     scrap
    -0.60
    POSITIVE LOGITS
    Their
    1.04
    Among
    1.02
    Others
    1.02
    Advertisement
    1.02
    Mount
    1.01
    Each
    1.01
    Commercial
    1.01
    Advertisements
    1.00
    Thus
    0.98
    These
    0.98
    Activations Density 0.861%

    No Known Activations