© 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. 21986
    Prev
    Next
    INDEX
    Explanations

    specific actions taken by different entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "did" and its context in relation to actions

    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
    astern
    -0.71
    EPA
    -0.70
    inational
    -0.69
    é¾įå
    -0.69
    istani
    -0.67
    isl
    -0.66
    zin
    -0.65
    clair
    -0.65
    arest
    -0.65
    PF
    -0.64
    POSITIVE LOGITS
     its
    1.22
     Its
    1.15
     itself
    1.10
     ITS
    1.10
    Its
    0.95
     their
    0.85
     mascot
    0.81
     sponsoring
    0.81
     THEIR
    0.81
     Their
    0.81
    Activations Density 0.534%

    No Known Activations