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. 8-RES-JB
    6. 18855
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or emphasize a point or idea

    oai_token-act-pair · gpt-3.5-turbo

    important concepts or statements prefixed by "the thing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥı
    -0.66
    chlor
    -0.65
    AGES
    -0.63
    ãĥĭ
    -0.61
    endars
    -0.61
    swick
    -0.60
     inflic
    -0.59
    Frag
    -0.59
    ulent
    -0.59
     Essex
    -0.57
    POSITIVE LOGITS
     thing
    0.88
     misconception
    0.81
    Quote
    0.80
     recurring
    0.77
     contrad
    0.76
     caveat
    0.76
     takeaway
    0.76
     kicker
    0.74
    iphany
    0.71
     truth
    0.71
    Activations Density 0.501%

    No Known Activations