Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23757
    Prev
    Next
    INDEX
    Explanations

    characters separating lines or sections in text

    oai_token-act-pair · gpt-3.5-turbo

    sequences of underscores or similar characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovan
    -0.78
    esan
    -0.71
    ymph
    -0.67
     Sea
    -0.63
    ois
    -0.62
    åĬ
    -0.60
    ways
    -0.60
    osc
    -0.60
     Wiley
    -0.59
     BMC
    -0.59
    POSITIVE LOGITS
    kw
    0.93
     ___
    0.82
    dict
    0.80
    /_
    0.80
     arrang
    0.79
    taboola
    0.78
    ___
    0.78
    PDATE
    0.78
    LINE
    0.77
     rall
    0.75
    Activations Density 0.009%

    No Known Activations