© 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. 9-RES-JB
    11. 3242
    Prev
    Next
    INDEX
    Explanations

    titles or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to authority figures and political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esters
    -0.85
    ooters
    -0.76
    ertodd
    -0.71
    etsk
    -0.70
    nob
    -0.67
    neapolis
    -0.67
    heon
    -0.66
    engers
    -0.64
    ellect
    -0.64
    mble
    -0.64
    POSITIVE LOGITS
     equivalent
    0.91
    's
    0.86
     signature
    0.80
    wide
    0.77
     favorite
    0.77
     invention
    0.75
     hallmark
    0.74
     fault
    0.74
     Presents
    0.73
     logo
    0.72
    Activations Density 0.943%

    No Known Activations