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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 422
    Prev
    Next
    INDEX
    Explanations

    words related to censorship or critical viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    terms related to censorship

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

    No Comments

    Negative Logits
     Dragonbound
    -0.78
     Goo
    -0.74
    ¯¯¯¯¯¯¯¯
    -0.73
     Rebellion
    -0.72
     Valhalla
    -0.67
     Hipp
    -0.66
     Werewolf
    -0.66
    RESULTS
    -0.65
     Tet
    -0.65
     Donetsk
    -0.63
    POSITIVE LOGITS
    orious
    1.13
     cens
    1.13
    orable
    1.10
    oring
    1.08
    orial
    0.91
    pling
    0.90
    ¦
    0.87
    urable
    0.87
    ovy
    0.86
    ured
    0.85
    Activations Density 0.011%

    No Known Activations