© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 13704
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and ethical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uart
    -0.71
    leans
    -0.67
    ridor
    -0.61
    ortment
    -0.60
    visual
    -0.59
    cean
    -0.59
    knit
    -0.58
     prepar
    -0.58
    ript
    -0.58
     resid
    -0.57
    POSITIVE LOGITS
     unjust
    0.83
     bullies
    0.82
     injustice
    0.74
     tresp
    0.73
     cowardly
    0.73
     slander
    0.71
     abusive
    0.70
     unfair
    0.69
     harassment
    0.69
     merciless
    0.68
    Activations Density 0.790%

    No Known Activations