© 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. 15984
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or plans in a professional or organizational context

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and auxiliary verbs indicating actions or states

    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
    verse
    -0.67
    communication
    -0.65
    division
    -0.64
    bies
    -0.63
    lio
    -0.62
    uffs
    -0.60
    angering
    -0.59
    iatus
    -0.58
    donald
    -0.57
    apper
    -0.57
    POSITIVE LOGITS
     therefore
    0.89
     however
    0.88
     also
    0.88
     furthermore
    0.85
     moreover
    0.83
     meanwhile
    0.76
     certainly
    0.69
     ital
    0.66
     hardly
    0.63
     additionally
    0.63
    Activations Density 1.270%

    No Known Activations