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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1158
    Prev
    Next
    INDEX
    Explanations

    references to posting or sharing content on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "posted" 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
    osi
    -0.72
    kos
    -0.70
    glers
    -0.69
    schild
    -0.67
    fts
    -0.64
    wing
    -0.63
    ppo
    -0.63
    Iv
    -0.63
    mentation
    -0.62
     Flavoring
    -0.62
    POSITIVE LOGITS
    hum
    0.96
    ulate
    0.94
     online
    0.87
    mortem
    0.84
     postings
    0.83
    onymous
    0.81
     pics
    0.79
     prominently
    0.78
     anonymously
    0.77
    gres
    0.76
    Activations Density 0.046%

    No Known Activations