© 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. 8-RES-JB
    11. 4623
    Prev
    Next
    INDEX
    Explanations

    phrases related to respect and following rules or authorities

    oai_token-act-pair · gpt-3.5-turbo

    the concept of respect in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bang
    -0.72
    trap
    -0.68
    clerosis
    -0.67
    rap
    -0.65
     dreamed
    -0.65
    igm
    -0.64
    cum
    -0.64
    mort
    -0.63
    wig
    -0.63
    ̶
    -0.63
    POSITIVE LOGITS
    ably
    1.00
    lessly
    0.85
    enance
    0.83
    fully
    0.80
     him
    0.76
     them
    0.72
     freedoms
    0.66
    amental
    0.66
     traditions
    0.65
     freedom
    0.63
    Activations Density 0.145%

    No Known Activations