© 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 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. 3878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating undermining or weakening something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that undermine authority or credibility

    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
    ————
    -0.79
    saw
    -0.68
    replace
    -0.67
     followed
    -0.67
    gat
    -0.66
     differs
    -0.65
     avoids
    -0.63
    bg
    -0.63
    tackle
    -0.62
    aido
    -0.62
    POSITIVE LOGITS
     entirety
    1.29
     entire
    1.17
     seriousness
    1.15
     effectiveness
    1.13
     possibility
    1.12
     notion
    1.12
     usefulness
    1.07
     ability
    1.06
     validity
    1.05
     credibility
    1.04
    Activations Density 0.265%

    No Known Activations