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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12829
    Prev
    Next
    INDEX
    Explanations

    words related to film screenings and premieres

    oai_token-act-pair · gpt-3.5-turbo

    terms related to film screenings and premieres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.89
    arine
    -0.75
    uria
    -0.70
    ippery
    -0.69
    avis
    -0.69
    abul
    -0.69
    mere
    -0.67
     drainage
    -0.66
    orically
    -0.66
    imb
    -0.66
    POSITIVE LOGITS
     starring
    1.00
     date
    0.96
     studio
    0.93
     premiere
    0.91
     schedule
    0.91
     reel
    0.90
     Deadline
    0.88
     studios
    0.88
    dates
    0.87
     trailer
    0.86
    Activations Density 0.143%

    No Known Activations