© 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 EvalsExportsAPI 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. 1012
    Prev
    Next
    INDEX
    Explanations

    words related to beginning or starting an action or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental or organizational actions and investigations

    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
     pedals
    -0.80
    osponsors
    -0.77
     ponies
    -0.72
     lyrics
    -0.69
    orthy
    -0.69
    atell
    -0.68
    wered
    -0.67
     buttons
    -0.66
     Bars
    -0.65
     belonged
    -0.65
    POSITIVE LOGITS
     discussion
    1.08
     flurry
    1.04
     barrage
    0.99
     consultation
    0.95
     vigorous
    0.95
     concerted
    0.94
     takeover
    0.94
     lengthy
    0.93
     spate
    0.93
     whirlwind
    0.92
    Activations Density 0.393%

    No Known Activations