© 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. 10-RES-JB
    11. 14131
    Prev
    Next
    INDEX
    Explanations

    phrases related to respect for principles, rights, freedoms, and ownership

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to respect and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quit
    -0.74
    cin
    -0.73
    itis
    -0.72
    starter
    -0.72
    oggle
    -0.71
     ASAP
    -0.71
    fix
    -0.71
    addon
    -0.70
    apter
    -0.69
    isode
    -0.68
    POSITIVE LOGITS
     traditions
    1.22
     individuality
    1.11
     elders
    1.11
     dignity
    1.05
     tradition
    1.01
     liberties
    1.00
     freedoms
    0.98
     sentiments
    0.97
     opinions
    0.96
     privacy
    0.95
    Activations Density 0.242%

    No Known Activations