© 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. 8-RES-JB
    11. 12791
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases highlighting communication and collaboration challenges

    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
    surprisingly
    -0.61
    itled
    -0.56
     Finder
    -0.54
    aired
    -0.54
     "$
    -0.54
    hered
    -0.53
    Fan
    -0.52
    described
    -0.51
    brew
    -0.51
    tained
    -0.51
    POSITIVE LOGITS
    '."
    1.32
    .'"
    1.31
    )."
    1.28
    ."
    1.19
    ]."
    1.14
    .''
    1.11
     âĢ¦"
    1.05
    ."[
    1.05
    .'
    1.05
    .")
    1.02
    Activations Density 1.021%

    No Known Activations