© 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. 1602
    Prev
    Next
    INDEX
    Explanations

    references to animated films

    oai_token-act-pair · gpt-3.5-turbo

    references to animation and animated content

    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
     Dod
    -1.05
     dod
    -0.74
     gol
    -0.71
    ktop
    -0.70
     Learns
    -0.69
     ellipt
    -0.69
     Typhoon
    -0.66
     acknow
    -0.66
     surn
    -0.64
     Woodward
    -0.64
    POSITIVE LOGITS
    anim
    3.76
    fil
    1.63
    animous
    1.54
    Anim
    1.53
    agar
    1.49
    anity
    1.14
    mag
    1.11
    animal
    1.11
    hazard
    1.08
    medi
    1.05
    Activations Density 0.023%

    No Known Activations