© 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. 8-RES-JB
    11. 8280
    Prev
    Next
    INDEX
    Explanations

    statements describing beliefs or thoughts about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating belief or speculation regarding information

    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
    ECK
    -0.79
    Interstitial
    -0.72
    awk
    -0.68
    ample
    -0.66
    mentioned
    -0.65
    avier
    -0.65
    claimer
    -0.63
    unciation
    -0.63
    ggies
    -0.62
    ENSE
    -0.61
    POSITIVE LOGITS
    fully
    0.72
    ril
    0.70
    liest
    0.69
     extinct
    0.69
    lessly
    0.68
     clinically
    0.68
    ocry
    0.67
     confid
    0.66
     anecd
    0.65
    onymous
    0.65
    Activations Density 0.091%

    No Known Activations