© 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. 0-RES-JB
    11. 22376
    Prev
    Next
    INDEX
    Explanations

    expressions related to a significant or considerable amount of something

    oai_token-act-pair · gpt-3.5-turbo

    quantities or portions related to money or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Instructor
    -0.84
    âĹı
    -0.70
    rology
    -0.68
     Honor
    -0.67
     Fischer
    -0.66
     Trials
    -0.66
     âĹı
    -0.65
    inus
    -0.65
    Î
    -0.65
    ivities
    -0.64
    POSITIVE LOGITS
     chunk
    3.41
     chunks
    3.10
     swath
    1.41
     slice
    1.39
     lump
    1.28
     slab
    1.26
     blob
    1.23
     shards
    1.05
     slices
    1.04
     bucket
    1.02
    Activations Density 0.017%

    No Known Activations