© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10700
    Prev
    Next
    INDEX
    Explanations

    titles or headlines containing ellipses

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or indications of continuation in writing

    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
    istically
    -0.73
    ality
    -0.67
     antip
    -0.67
     outl
    -0.67
    ally
    -0.67
     attest
    -0.66
    hetto
    -0.64
     cohesion
    -0.63
    lor
    -0.63
     oxide
    -0.62
    POSITIVE LOGITS
    BUT
    1.02
     âĢİ
    0.91
    until
    0.85
    yet
    0.84
    WIN
    0.83
    wait
    0.80
    BU
    0.80
    Sab
    0.79
    gone
    0.76
    they
    0.76
    Activations Density 0.041%

    No Known Activations