© 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. 12607
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and phrases indicating assessment or comparison

    oai_token-act-pair · gpt-3.5-turbo

    mention of strong emotional or impactful statements

    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
    apo
    -0.77
    ogun
    -0.73
    acs
    -0.66
    LC
    -0.65
    ieu
    -0.63
    rolling
    -0.61
    oj
    -0.61
    igators
    -0.61
    erg
    -0.60
     Secondly
    -0.59
    POSITIVE LOGITS
     downright
    1.09
     quite
    0.77
     even
    0.75
     worse
    0.73
     pretty
    0.69
    ADRA
    0.67
     entire
    0.67
     barely
    0.67
     mere
    0.65
     nonexistent
    0.65
    Activations Density 0.288%

    No Known Activations