© 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. 16299
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming or technical terms, especially those involving specific syntax or keywords

    oai_token-act-pair · gpt-3.5-turbo

    the word "gnu."

    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
     simulator
    -0.71
    utterstock
    -0.71
    roma
    -0.71
    vil
    -0.68
    VEN
    -0.63
    spection
    -0.61
     WATCH
    -0.60
     motiv
    -0.60
    washing
    -0.60
    chieve
    -0.59
    POSITIVE LOGITS
     Alz
    0.68
    abil
    0.65
    20439
    0.63
    CG
    0.61
     franc
    0.61
    mag
    0.61
    Pres
    0.60
    ocide
    0.59
    Tokens
    0.59
     chancellor
    0.59
    Activations Density 0.000%

    No Known Activations