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

    Neuronpedia

    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. 2473
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental attitude and productivity

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions and repeated phrases indicating continuity or addition

    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
    ãĤ´ãĥ³
    -0.77
     ®
    -0.70
    zu
    -0.65
    apor
    -0.65
    hered
    -0.63
    !:
    -0.63
    antine
    -0.61
    ãĥĭ
    -0.61
    iren
    -0.59
    successfully
    -0.57
    POSITIVE LOGITS
     blah
    1.14
     stuff
    1.10
     everybody
    1.04
    romeda
    1.02
     yeah
    0.97
     maybe
    0.93
     secondly
    0.93
     hopefully
    0.92
     frankly
    0.90
     somebody
    0.88
    Activations Density 0.323%

    No Known Activations