© 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. 7907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating demonstration, showing, or illustrating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating evidence or illustrative examples

    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
    ades
    -0.85
    agues
    -0.76
    queue
    -0.71
    ade
    -0.70
     freezes
    -0.67
     externalToEVAOnly
    -0.67
    porary
    -0.63
    requ
    -0.62
     Referred
    -0.60
    atri
    -0.60
    POSITIVE LOGITS
     weakness
    0.90
     how
    0.87
     impat
    0.80
     maturity
    0.79
     weaknesses
    0.79
     emptiness
    0.77
     desperation
    0.77
     incompetence
    0.76
     humility
    0.75
     displeasure
    0.75
    Activations Density 0.130%

    No Known Activations