© 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. 0-RES-JB
    11. 12895
    Prev
    Next
    INDEX
    Explanations

    phrases related to being convinced or certain about something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty and persuasion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ew
    -0.74
    umbers
    -0.71
     Cooldown
    -0.67
    umber
    -0.67
     flow
    -0.66
    imb
    -0.64
     =>
    -0.63
    rawl
    -0.63
     birth
    -0.61
     downtime
    -0.61
    POSITIVE LOGITS
     convinced
    3.37
     persuaded
    2.65
     convin
    1.96
     convince
    1.82
     reassured
    1.61
     convincing
    1.56
     impressed
    1.52
     lured
    1.48
     fooled
    1.42
     intrigued
    1.42
    Activations Density 0.012%

    No Known Activations