© 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. 23657
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "full" used in the context of describing the complete or total nature, extent, or scope of something

    oai_token-act-pair · gpt-3.5-turbo

    references to completeness and full scope or extent of various subjects

    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
    ako
    -0.65
     Slowly
    -0.64
    Tickets
    -0.63
    orers
    -0.63
    icho
    -0.62
     Tracks
    -0.61
     destro
    -0.61
     ashore
    -0.61
    atto
    -0.60
    ummies
    -0.60
    POSITIVE LOGITS
     extent
    1.31
     brunt
    1.21
     spectrum
    1.10
     complement
    1.09
     scope
    1.02
    ness
    1.00
     range
    0.92
    hearted
    0.89
     breadth
    0.88
     frontal
    0.87
    Activations Density 0.037%

    No Known Activations