© 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. 6966
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviewing or analyzing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "review" and its variations

    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
    Torrent
    -0.75
    trap
    -0.71
    vic
    -0.70
    guard
    -0.70
    arak
    -0.68
    lez
    -0.68
    bott
    -0.66
    cil
    -0.66
    iac
    -0.65
    starter
    -0.64
    POSITIVE LOGITS
    ively
    0.86
     whether
    0.77
     favorably
    0.76
     how
    0.75
     carefully
    0.74
     incoming
    0.73
     feasibility
    0.72
     them
    0.71
     closely
    0.69
     trends
    0.69
    Activations Density 0.196%

    No Known Activations