© 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. 4-RES-JB
    11. 22100
    Prev
    Next
    INDEX
    Explanations

    the word "binge" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to binge-watching and related behaviors

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

    No Comments

    Negative Logits
    ando
    -0.79
    nil
    -0.74
    OST
    -0.72
    ioned
    -0.71
     Nare
    -0.68
    UTION
    -0.67
    anim
    -0.67
    amoto
    -0.66
    ansom
    -0.66
    iage
    -0.65
    POSITIVE LOGITS
     binge
    0.97
     bul
    0.90
    inge
    0.86
    âĸ¬
    0.75
     eaves
    0.74
     harb
    0.71
     clen
    0.70
     episodes
    0.69
     hoard
    0.69
     empt
    0.68
    Activations Density 0.021%

    No Known Activations