© 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. 3-RES-JB
    11. 8911
    Prev
    Next
    INDEX
    Explanations

    mentions of something being showcased, highlighted, or displayed prominently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "featured" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.93
    apa
    -0.85
    thur
    -0.83
    alty
    -0.76
    uth
    -0.73
    aut
    -0.69
    kos
    -0.68
    ça
    -0.66
    sequence
    -0.66
    oner
    -0.66
    POSITIVE LOGITS
     prominently
    1.45
    Featured
    0.90
    Feature
    0.87
     featured
    0.82
    features
    0.81
     features
    0.81
     Features
    0.80
    ãĤ´
    0.75
    Features
    0.73
     Include
    0.72
    Activations Density 0.018%

    No Known Activations