© 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. 11-RES-JB
    11. 14916
    Prev
    Next
    INDEX
    Explanations

    dates or time-related references

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    phabet
    -0.77
    ãĤ¤ãĥĪ
    -0.69
    ocial
    -0.66
    thood
    -0.65
    abilia
    -0.64
    ata
    -0.63
    eanor
    -0.62
    vich
    -0.61
    aternity
    -0.61
    few
    -0.60
    POSITIVE LOGITS
     behest
    1.61
     expense
    1.28
     urging
    1.23
     insistence
    1.19
     height
    1.17
     outset
    1.17
     request
    1.16
     ripe
    1.08
     invitation
    1.07
     suggestion
    1.03
    Activations Density 0.081%

    No Known Activations