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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22554
    Prev
    Next
    INDEX
    Explanations

    phrases using the term "much"

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating a high degree of emphasis 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
    ogi
    -0.72
    ortmund
    -0.72
    alez
    -0.71
    aring
    -0.71
    yson
    -0.71
    AMY
    -0.68
    iere
    -0.66
    oft
    -0.66
    orer
    -0.65
    OA
    -0.64
    POSITIVE LOGITS
     worthless
    0.83
     identical
    0.82
     everywhere
    0.81
     everything
    0.80
     nailed
    0.80
     useless
    0.80
    everything
    0.79
     nil
    0.75
     boils
    0.74
     intact
    0.73
    Activations Density 0.065%

    No Known Activations