© 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. 6-RES-JB
    11. 9341
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    linguistic variations of the verb “to be” and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scand
    -0.64
     Kos
    -0.63
     Pyramid
    -0.58
     Nem
    -0.58
     Annotations
    -0.57
     Line
    -0.56
     Piano
    -0.56
     Explosion
    -0.56
     Noise
    -0.56
     Nou
    -0.56
    POSITIVE LOGITS
    ifully
    0.98
    efully
    0.92
    ted
    0.86
    ingly
    0.85
    antly
    0.82
    rarily
    0.82
    ishly
    0.82
    gered
    0.80
    ulously
    0.80
    kered
    0.79
    Activations Density 0.203%

    No Known Activations