© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5385
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an evaluation of something as being of optimal quality or behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the quality or credibility of information or opinions

    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
    kefeller
    -0.78
    aternity
    -0.70
    bath
    -0.65
    essor
    -0.64
    uph
    -0.63
     hurd
    -0.62
    omed
    -0.60
    ipal
    -0.60
    quit
    -0.59
     ensu
    -0.58
    POSITIVE LOGITS
     glance
    1.06
     blush
    0.70
     approximation
    0.69
    hiba
    0.68
    aic
    0.67
    arb
    0.67
    lehem
    0.67
     superficial
    0.65
     rudimentary
    0.65
     intermittent
    0.65
    Activations Density 0.026%

    No Known Activations