© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10380
    Prev
    Next
    INDEX
    Explanations

    words related to human figures

    oai_token-act-pair · gpt-3.5-turbo

    references to various figures of speech or metaphorical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAQ
    -0.75
    ModLoader
    -0.72
    cyclopedia
    -0.71
    ntil
    -0.70
    IFE
    -0.69
    é¾
    -0.67
    umenthal
    -0.67
    artney
    -0.67
    esis
    -0.67
    ãĥ¯ãĥ³
    -0.66
    POSITIVE LOGITS
    head
    1.11
    heads
    1.03
     skating
    1.02
     prominently
    1.01
    downs
    0.82
    enance
    0.79
    collection
    0.74
    books
    0.73
    acements
    0.72
     macros
    0.70
    Activations Density 0.041%

    No Known Activations