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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12533
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing or highlighting certain aspects

    oai_token-act-pair · gpt-3.5-turbo

    instances of uncertainty or ambiguity in statements

    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
     shitty
    -0.72
     hating
    -0.71
     Protector
    -0.71
     whining
    -0.70
     whine
    -0.69
     fucking
    -0.65
     Infinite
    -0.63
     grieving
    -0.63
     selfish
    -0.63
     Anon
    -0.62
    POSITIVE LOGITS
    odox
    0.93
    ãĥĥãĥĪ
    0.90
    ãĥķãĤ©
    0.86
    reet
    0.86
    ãĤ©
    0.77
    ãĥij
    0.77
     teasp
    0.75
    qqa
    0.74
    ould
    0.72
    ufficient
    0.72
    Activations Density 1.186%

    No Known Activations