Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16687
    Prev
    Next
    INDEX
    Explanations

    mentions of the aircraft company Boeing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the aircraft manufacturer Boeing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atro
    -0.86
    olkien
    -0.82
    avez
    -0.80
    odic
    -0.80
    arios
    -0.73
    ablishment
    -0.72
    itia
    -0.72
    ourced
    -0.70
    arist
    -0.69
    laus
    -0.67
    POSITIVE LOGITS
     Airlines
    0.80
     Industries
    0.76
     777
    0.75
    heed
    0.75
     737
    0.75
     airplanes
    0.74
     Corporation
    0.73
     747
    0.73
    etooth
    0.72
     Company
    0.69
    Activations Density 0.011%

    No Known Activations