© 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. 4-RES-JB
    11. 2005
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is highlighted as the sole or main example of a particular category or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "only."

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

    No Comments

    Negative Logits
    regate
    -0.68
    ãĤ©
    -0.68
    è»
    -0.67
     Mub
    -0.64
    each
    -0.62
     Morph
    -0.62
     Harmony
    -0.61
    interstitial
    -0.61
    mass
    -0.61
    chlor
    -0.61
    POSITIVE LOGITS
     logical
    0.84
     thing
    0.79
    £ı
    0.78
     valid
    0.71
     clue
    0.69
     solution
    0.69
     conceivable
    0.67
     consolation
    0.66
     avenue
    0.66
     drawback
    0.65
    Activations Density 0.022%

    No Known Activations