© 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. 8634
    Prev
    Next
    INDEX
    Explanations

    ellipses (...) or incomplete sentences

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or pauses in text

    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
    istically
    -0.83
    ally
    -0.80
     outl
    -0.76
    ality
    -0.76
     vig
    -0.66
     comparisons
    -0.66
     prosperity
    -0.65
     weight
    -0.65
     antip
    -0.65
     lip
    -0.65
    POSITIVE LOGITS
     âĢİ
    0.93
    CLASSIFIED
    0.84
    ↵Âł
    0.77
    BUT
    0.77
     Appears
    0.76
    Draft
    0.76
    aughs
    0.75
     Attend
    0.73
    ļéĨĴ
    0.70
    Building
    0.70
    Activations Density 0.040%

    No Known Activations