© 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. 8-RES-JB
    11. 11248
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and competition

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases with numerous commas or pauses

    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
    ppo
    -0.77
    hub
    -0.76
    ire
    -0.75
    orem
    -0.71
    pec
    -0.70
    "]=>
    -0.70
    bucks
    -0.68
    aimon
    -0.66
    chell
    -0.66
    izen
    -0.65
    POSITIVE LOGITS
     allowing
    1.25
     culminating
    1.24
     prompting
    1.24
     preferring
    1.19
     emphasizing
    1.17
     earning
    1.15
     citing
    1.13
     claiming
    1.11
     including
    1.11
     forcing
    1.11
    Activations Density 0.503%

    No Known Activations