© 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. 18150
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or states that involve a significant change or impact

    oai_token-act-pair · gpt-3.5-turbo

    actions related to control, manipulation, or influence

    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
    ItemTracker
    -0.55
     dotted
    -0.54
    Downloadha
    -0.52
     Nos
    -0.48
    likely
    -0.47
     fashioned
    -0.45
     Mehran
    -0.45
    nikov
    -0.45
     TBA
    -0.45
    dating
    -0.45
    POSITIVE LOGITS
    uate
    0.74
    ISE
    0.69
    itate
    0.63
    igate
    0.63
    enance
    0.61
    IRE
    0.56
    oshop
    0.56
    ANGE
    0.56
    ulate
    0.54
    ENGTH
    0.54
    Activations Density 0.803%

    No Known Activations