© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13149
    Prev
    Next
    INDEX
    Explanations

    keywords related to censorship

    oai_token-act-pair · gpt-3.5-turbo

    references to censorship and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lakes
    -0.78
    verty
    -0.75
    laus
    -0.74
    thritis
    -0.72
    amac
    -0.72
    ndra
    -0.71
     Dew
    -0.68
    ovember
    -0.67
    erald
    -0.66
    ptoms
    -0.66
    POSITIVE LOGITS
     censorship
    1.25
     cens
    1.14
     censor
    1.10
     censored
    1.06
     commissions
    0.75
     suppressing
    0.74
     blackout
    0.74
     inhib
    0.73
    ourgeois
    0.72
     screenings
    0.71
    Activations Density 0.009%

    No Known Activations