© 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. 7786
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis on the level of something being significant or notable

    oai_token-act-pair · gpt-3.5-turbo

    the word "quite" and its variations in usage context

    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
    elsen
    -0.84
     DRAG
    -0.83
    venant
    -0.80
    ULTS
    -0.76
    ulkan
    -0.74
    erson
    -0.69
    ults
    -0.68
    PLIED
    -0.67
    interstitial
    -0.65
    orer
    -0.64
    POSITIVE LOGITS
     frankly
    1.00
     literally
    0.79
     alright
    0.74
     possibly
    0.71
     nice
    0.70
     nifty
    0.69
     tame
    0.68
     readable
    0.65
     Orwell
    0.65
     scary
    0.65
    Activations Density 0.026%

    No Known Activations