© 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. 0-RES-JB
    11. 10185
    Prev
    Next
    INDEX
    Explanations

    keywords related to episodes in a series or TV show

    oai_token-act-pair · gpt-3.5-turbo

    references to episodic content, particularly related to episodes

    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
     fielding
    -0.69
    elligence
    -0.68
    rade
    -0.67
    ower
    -0.66
    ghai
    -0.64
     Gardner
    -0.64
     intimid
    -0.64
    ali
    -0.63
    loo
    -0.63
    illery
    -0.61
    POSITIVE LOGITS
     Ep
    3.90
    Ep
    3.02
     ep
    1.97
     Episode
    1.53
     EP
    1.48
     Epic
    1.48
    ep
    1.44
     epilepsy
    1.31
     epist
    1.29
     Lep
    1.26
    Activations Density 0.012%

    No Known Activations