© 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. 4228
    Prev
    Next
    INDEX
    Explanations

    online profiles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Profile" and related terms indicating user profiles

    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
    assic
    -0.92
    ricular
    -0.86
    nesday
    -0.73
    ibility
    -0.67
    unal
    -0.67
    abeth
    -0.66
    heed
    -0.64
     heed
    -0.64
    ensical
    -0.63
    ply
    -0.63
    POSITIVE LOGITS
     Joined
    1.49
     Blog
    1.27
     Occupations
    0.91
    Joined
    0.85
     {:
    0.83
     Posts
    0.80
     DevOnline
    0.79
     Profile
    0.75
     Expand
    0.74
     Marketable
    0.73
    Activations Density 0.016%

    No Known Activations