© 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. 7-RES-JB
    11. 22884
    Prev
    Next
    INDEX
    Explanations

    phrases related to official divisions or sections

    oai_token-act-pair · gpt-3.5-turbo

    instances of divisions or categories within organizations, sports, or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steen
    -0.71
    Shell
    -0.70
    Cola
    -0.70
    netflix
    -0.70
    ITH
    -0.69
    ndra
    -0.69
    Benz
    -0.68
    ãĤ¼
    -0.67
    kie
    -0.67
    ãĤ«
    -0.66
    POSITIVE LOGITS
    incial
    0.69
    ular
    0.66
    uties
    0.63
    xus
    0.62
    INAL
    0.62
    omal
    0.61
    :]
    0.61
     consolidation
    0.61
     Sabha
    0.61
     Veteran
    0.60
    Activations Density 0.483%

    No Known Activations