© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 2021
    Prev
    Next
    INDEX
    Explanations

    phrases or keywords that 'highlight' or 'continue' a story

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating highlights or important events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lia
    -0.76
    bid
    -0.65
     kits
    -0.65
    flo
    -0.65
    folk
    -0.64
    GM
    -0.64
    road
    -0.64
    wing
    -0.63
    rop
    -0.62
    owners
    -0.62
    POSITIVE LOGITS
     Thumbnails
    1.13
     Transcript
    0.84
     Continued
    0.84
    Interstitial
    0.84
     ..........
    0.84
     Flavoring
    0.84
    CLASSIFIED
    0.81
     Loading
    0.80
    allery
    0.80
    indal
    0.78
    Activations Density 0.082%

    No Known Activations