© 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. 22848
    Prev
    Next
    INDEX
    Explanations

    positive opinions or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or opinion

    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
    è¦ļéĨĴ
    -0.74
     destro
    -0.69
    adra
    -0.66
     dictates
    -0.66
    aughters
    -0.66
    ×Ļ
    -0.66
    untled
    -0.64
     sidx
    -0.64
    ç«
    -0.63
    WER
    -0.63
    POSITIVE LOGITS
     innocuous
    0.73
     joking
    0.72
     kindred
    0.72
     invincible
    0.71
     gonna
    0.68
     harmless
    0.66
     funny
    0.66
     unbeat
    0.65
     kidding
    0.65
     cute
    0.64
    Activations Density 0.179%

    No Known Activations