© 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. 6-RES-JB
    11. 17405
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to thinking about or discussing something

    oai_token-act-pair · gpt-3.5-turbo
    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
    steen
    -0.69
    rams
    -0.64
     Colo
    -0.64
    strom
    -0.63
     Towns
    -0.63
     Lar
    -0.61
     Greens
    -0.60
     Preston
    -0.59
    poons
    -0.59
     Pirates
    -0.58
    POSITIVE LOGITS
    chy
    1.01
    alian
    0.91
    self
    0.84
     happening
    0.82
    atical
    0.80
    atic
    0.80
     beforehand
    0.79
     raining
    0.75
     happens
    0.74
    MpServer
    0.74
    Activations Density 0.102%

    No Known Activations