© 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. 22257
    Prev
    Next
    INDEX
    Explanations

    quantitative terms related to amounts or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of quantity or magnitude

    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
    ilities
    -0.74
    imens
    -0.68
    Pic
    -0.67
    missions
    -0.67
    umbn
    -0.66
    ivals
    -0.66
    ours
    -0.65
    ubs
    -0.64
    otos
    -0.64
    atches
    -0.63
    POSITIVE LOGITS
     anymore
    0.78
    bang
    0.71
    efeated
    0.70
    !!!!
    0.69
    !?
    0.65
    !!!!!
    0.62
     Archdemon
    0.62
    sword
    0.61
     Kappa
    0.61
    !?"
    0.59
    Activations Density 0.062%

    No Known Activations