© 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. 11-RES-JB
    11. 11804
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative criticism or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases highlighting the consequences or effects of policies or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.74
    oubted
    -0.72
    »Ĵ
    -0.71
    rete
    -0.71
    escription
    -0.71
    itness
    -0.70
    dozen
    -0.70
    overed
    -0.70
    atted
    -0.70
    vered
    -0.69
    POSITIVE LOGITS
     undermines
    1.75
     hurts
    1.68
     destroys
    1.68
     harms
    1.65
     violates
    1.53
     threatens
    1.52
     wastes
    1.51
     inhibits
    1.49
     discour
    1.46
     ignores
    1.46
    Activations Density 0.351%

    No Known Activations