© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21070
    Prev
    Next
    INDEX
    Explanations

    terms related to global markets and segments, particularly focusing on various industries and regions

    oai_token-act-pair · gpt-3.5-turbo

    instances of varied and repeated conjunctions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alion
    -0.67
    ebus
    -0.67
    ©¶æ
    -0.67
    erton
    -0.65
    amaz
    -0.65
    maxwell
    -0.65
    Optional
    -0.64
    orde
    -0.64
     Nope
    -0.63
    ashed
    -0.62
    POSITIVE LOGITS
     ranging
    1.17
     culminating
    1.09
     influencing
    1.06
     spanning
    1.03
     attracting
    1.01
     including
    0.96
     fueling
    0.95
    ranging
    0.94
     benefiting
    0.93
     incorporating
    0.92
    Activations Density 0.351%

    No Known Activations