© 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. 4234
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a specific amount or quantity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize specific words or concepts related to verbal assertions and communication

    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
     generational
    -0.67
    çī
    -0.66
     dich
    -0.63
    thumbnails
    -0.62
     polarized
    -0.62
     types
    -0.60
    types
    -0.59
     paraph
    -0.59
     polar
    -0.59
    idon
    -0.58
    POSITIVE LOGITS
     dime
    1.03
     ounce
    0.90
    ODY
    0.89
    THING
    0.87
    hower
    0.85
    baugh
    0.79
     whatsoever
    0.75
    BLE
    0.74
     whiff
    0.73
     EVER
    0.71
    Activations Density 0.267%

    No Known Activations