© 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 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. 7-RES-JB
    11. 20754
    Prev
    Next
    INDEX
    Explanations

    instances of text referring to public or online postings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "posted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kos
    -0.71
    glers
    -0.69
     Brill
    -0.67
     Gand
    -0.65
    Iv
    -0.64
    osi
    -0.64
     Flavoring
    -0.64
     Nebula
    -0.63
     Galile
    -0.61
    cest
    -0.61
    POSITIVE LOGITS
    hum
    0.96
    ulate
    0.93
     postings
    0.86
     prominently
    0.80
     online
    0.78
    mortem
    0.78
     pics
    0.78
    onymous
    0.77
    posted
    0.77
    gres
    0.76
    Activations Density 0.037%

    No Known Activations