© 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. 8-RES-JB
    11. 4196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or addition with an emphasis on the latter

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    case
    -0.72
    oward
    -0.68
    IS
    -0.68
    ACT
    -0.67
    azo
    -0.66
    irie
    -0.64
    real
    -0.64
    ument
    -0.64
    utenberg
    -0.63
    ãĥģ
    -0.63
    POSITIVE LOGITS
     hence
    1.18
     consequently
    1.12
     therefore
    1.09
     thus
    1.06
     moreover
    0.98
     although
    0.96
     furthermore
    0.93
     luckily
    0.92
     secondly
    0.90
     fortunately
    0.87
    Activations Density 0.361%

    No Known Activations