© 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. 3-RES-JB
    11. 18103
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ended" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esis
    -0.80
    ña
    -0.78
    appa
    -0.75
    itsch
    -0.74
    htaking
    -0.71
    hee
    -0.70
    alty
    -0.70
    issance
    -0.69
    arij
    -0.68
    icipated
    -0.67
    POSITIVE LOGITS
    angering
    0.99
    owment
    0.85
     abruptly
    0.84
     tragically
    0.81
    ocrin
    0.80
     prematurely
    0.79
     sidel
    0.70
    ocrine
    0.68
    orses
    0.64
    angers
    0.62
    Activations Density 0.034%

    No Known Activations