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

    Neuronpedia

    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. 7-RES-JB
    11. 4853
    Prev
    Next
    INDEX
    Explanations

    words related to personal opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating frequency or degree of certainty in actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raught
    -0.77
    igger
    -0.73
    urden
    -0.72
    ayers
    -0.71
    yne
    -0.70
    rend
    -0.70
    usterity
    -0.68
    umo
    -0.66
    illin
    -0.66
    iem
    -0.66
    POSITIVE LOGITS
     thereafter
    1.05
     consequently
    1.02
     invests
    0.98
     expects
    0.98
     replaces
    0.94
     secondly
    0.93
     proceeded
    0.93
     rely
    0.87
     anticipate
    0.86
     congratulate
    0.86
    Activations Density 0.210%

    No Known Activations