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. 3-RES-JB
    6. 2540
    Prev
    Next
    INDEX
    Explanations

    terms related to infrastructure and deployment

    oai_token-act-pair · gpt-3.5-turbo

    specific groups, objects, or concepts that indicate social or structural hierarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknowled
    -0.65
    yss
    -0.59
    NC
    -0.54
    âķIJâķIJ
    -0.54
    Moh
    -0.53
    BI
    -0.52
    FUL
    -0.51
    GAN
    -0.50
    OUT
    -0.49
    DATA
    -0.49
    POSITIVE LOGITS
    hips
    1.12
    hip
    0.96
    paces
    0.93
    hops
    0.90
    poons
    0.88
    ettings
    0.87
    mith
    0.87
    pace
    0.84
    uits
    0.83
    uggest
    0.82
    Activations Density 0.932%

    No Known Activations