© 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. 3-RES-JB
    11. 21283
    Prev
    Next
    INDEX
    Explanations

    mentions of words related to screens or scripts

    oai_token-act-pair · gpt-3.5-turbo

    references to "screen" or "screenwriters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipop
    -0.74
    ortium
    -0.72
    doms
    -0.71
    ghan
    -0.71
     Harriet
    -0.69
     deleg
    -0.68
    IGH
    -0.67
    ciating
    -0.66
    thens
    -0.64
     hypoc
    -0.63
    POSITIVE LOGITS
    plays
    1.28
     screens
    1.05
    screen
    1.04
     screen
    1.00
    writers
    0.97
    writer
    0.95
     TVs
    0.95
    room
    0.87
     Screen
    0.85
    reens
    0.83
    Activations Density 0.012%

    No Known Activations