© 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. 2-RES-JB
    11. 17477
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or business documents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of" in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brill
    -0.88
     stead
    -0.80
    brance
    -0.66
     outwe
    -0.63
    mares
    -0.62
     adm
    -0.60
    selves
    -0.60
     thous
    -0.60
     wedd
    -0.60
     inconsist
    -0.59
    POSITIVE LOGITS
    Writer
    0.83
    rite
    0.78
     Spiral
    0.75
    lime
    0.70
    Pak
    0.70
    knit
    0.69
    ruct
    0.67
    arial
    0.67
    Correct
    0.66
    Chapter
    0.66
    Activations Density 0.000%

    No Known Activations