© 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. 3253
    Prev
    Next
    INDEX
    Explanations

    comparative statements indicating an increased degree or level

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing increasing intensity or significance

    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
    gio
    -1.01
    ocene
    -0.80
    esan
    -0.72
    meet
    -0.71
    only
    -0.70
    ences
    -0.66
    cius
    -0.66
    uese
    -0.65
     Rapp
    -0.65
    medium
    -0.64
    POSITIVE LOGITS
     stringent
    0.89
     potent
    0.85
     impressive
    0.83
     ambitious
    0.81
     precarious
    0.78
     challeng
    0.76
     expensive
    0.74
     ardent
    0.74
     than
    0.74
     exciting
    0.74
    Activations Density 0.052%

    No Known Activations