© 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. 10-RES-JB
    11. 13953
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs or suspicions

    oai_token-act-pair · gpt-3.5-turbo

    words related to belief and suspicion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itect
    -0.77
    rawdownloadcloneembedreportprint
    -0.73
    phabet
    -0.72
    ãģį
    -0.71
    GBT
    -0.71
    ingen
    -0.70
    Liter
    -0.70
    ãĤ´ãĥ³
    -0.68
    ilver
    -0.67
    oliberal
    -0.67
    POSITIVE LOGITS
     foul
    1.05
     they
    0.95
     he
    0.95
     wrongdoing
    0.93
     she
    0.90
     there
    0.90
     Paddock
    0.86
     someone
    0.82
     something
    0.79
     that
    0.79
    Activations Density 0.225%

    No Known Activations