© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 56
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to explaining reasoning or principles behind actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "behind" or the origin of ideas

    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
     Pwr
    -0.80
    istic
    -0.76
    ander
    -0.73
    ERC
    -0.70
    cki
    -0.64
    ucc
    -0.63
    abo
    -0.62
    thritis
    -0.62
    quet
    -0.61
    owl
    -0.61
    POSITIVE LOGITS
    âĸ¬âĸ¬
    0.75
    paren
    0.70
     behind
    0.70
    ¬
    0.69
    actively
    0.66
    lined
    0.65
    world
    0.64
    standing
    0.64
    bys
    0.63
    tions
    0.63
    Activations Density 0.018%

    No Known Activations