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. 8-RES-JB
    6. 19684
    Prev
    Next
    INDEX
    Explanations

    tokens that represent commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    individual letters or character sequences that signify text or code elements

    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
     Ae
    -0.76
     Chosen
    -0.69
     undert
    -0.69
     Stones
    -0.67
     Founding
    -0.66
     Rolls
    -0.65
    idation
    -0.65
     Standing
    -0.65
     Manifest
    -0.65
     Thrones
    -0.64
    POSITIVE LOGITS
    td
    1.11
    tg
    1.10
    vc
    1.08
    dm
    1.05
    pg
    1.01
    sb
    1.01
    fw
    1.00
    sf
    0.99
    tp
    0.99
    vl
    0.97
    Activations Density 0.188%

    No Known Activations