© 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. 11018
    Prev
    Next
    INDEX
    Explanations

    terms related to specific people, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations and notable figures

    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
    displayText
    -0.46
     mouse
    -0.46
     adapted
    -0.45
    etheless
    -0.44
     sclerosis
    -0.44
     grate
    -0.44
     welcomed
    -0.44
    umbnails
    -0.43
     redistributed
    -0.43
     cytok
    -0.42
    POSITIVE LOGITS
     Therapy
    0.51
     Syndrome
    0.50
    gress
    0.49
    Ò
    0.48
     Rubin
    0.48
    opol
    0.47
    loe
    0.46
     Productions
    0.46
     Oval
    0.45
     Holdings
    0.44
    Activations Density 1.215%

    No Known Activations