© 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. 6-RES-JB
    11. 7847
    Prev
    Next
    INDEX
    Explanations

    the phrase "all of it" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express absolutes or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.69
    aminer
    -0.69
    lict
    -0.66
     DF
    -0.59
    IDS
    -0.59
     incre
    -0.58
     Mellon
    -0.58
    nant
    -0.57
    edin
    -0.57
    licts
    -0.56
    POSITIVE LOGITS
    ocating
    0.91
    iance
    0.86
    uring
    0.85
    ahu
    0.82
    usive
    0.80
    ogene
    0.80
    iter
    0.80
    ocation
    0.78
    ergic
    0.77
    owing
    0.75
    Activations Density 0.072%

    No Known Activations