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. 3338
    Prev
    Next
    INDEX
    Explanations

    specific names of universities

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and government entities, particularly in a state context

    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
    ï¸ı
    -0.91
    Frames
    -0.71
    etimes
    -0.67
    ï¸
    -0.67
    ipel
    -0.65
     Moonlight
    -0.64
    iasco
    -0.63
    errilla
    -0.63
    selves
    -0.62
     Stard
    -0.62
    POSITIVE LOGITS
    aucuses
    0.76
     trooper
    0.72
    hyde
    0.71
     troopers
    0.70
     reserve
    0.64
    sylvania
    0.64
     Pixie
    0.63
     Vera
    0.62
    itol
    0.61
     monopoly
    0.61
    Activations Density 0.215%

    No Known Activations