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. 2-RES-JB
    6. 9956
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of a specific abbreviation (NB) followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to the National Basketball Association (NBA)

    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
    tails
    -0.77
    gem
    -0.74
    othy
    -0.72
    æ©
    -0.72
    wig
    -0.71
    eve
    -0.68
    bral
    -0.66
    ãĥī
    -0.66
    ttle
    -0.66
    mons
    -0.65
    POSITIVE LOGITS
    NB
    0.84
    ionics
    0.80
    emonic
    0.80
    FN
    0.78
    UGE
    0.75
    endix
    0.73
    ued
    0.71
    axter
    0.70
    irm
    0.69
    thren
    0.67
    Activations Density 0.011%

    No Known Activations