© 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. 12-RES-JB
    11. 3305
    Prev
    Next
    INDEX
    Explanations

    phrases pointing out specific instances or examples

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oyer
    -0.74
    soDeliveryDate
    -0.74
    PASS
    -0.72
    nic
    -0.71
    rab
    -0.71
    kefeller
    -0.66
    ilities
    -0.65
    nia
    -0.65
    chy
    -0.63
    ILE
    -0.63
    POSITIVE LOGITS
     point
    0.98
     Point
    0.70
    point
    0.66
    file
    0.64
    EStreamFrame
    0.63
    matic
    0.62
    escap
    0.62
     Perspective
    0.60
     fact
    0.60
     particulars
    0.59
    Activations Density 0.067%

    No Known Activations