© 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. 6-RES-JB
    11. 11813
    Prev
    Next
    INDEX
    Explanations

    terms related to disorders, medical conditions, and medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "ore" and its variations, which likely relates to resources or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ued
    -0.76
     srf
    -0.76
    uing
    -0.74
    Ļ½
    -0.74
    uation
    -0.71
    ues
    -0.70
    ¬¼
    -0.70
    ulk
    -0.69
    arb
    -0.69
    urers
    -0.69
    POSITIVE LOGITS
    tto
    1.24
    tsky
    1.10
    byss
    1.07
    gon
    1.06
    tta
    1.02
    ttes
    0.98
    nz
    0.96
    lli
    0.95
    cki
    0.94
    tti
    0.94
    Activations Density 0.025%

    No Known Activations