© 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. 18518
    Prev
    Next
    INDEX
    Explanations

    words related to changes, plans, or agreements

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of aging

    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
    Reviewer
    -0.75
     sidel
    -0.75
    ihar
    -0.72
    STON
    -0.69
    anchester
    -0.63
    asca
    -0.63
     Rodham
    -0.61
    packing
    -0.60
    aird
    -0.60
    kefeller
    -0.60
    POSITIVE LOGITS
    hog
    1.03
    hig
    0.74
    ecake
    0.74
    orge
    0.71
    ury
    0.71
    avier
    0.70
    ql
    0.70
    ffiti
    0.67
    cliffe
    0.66
    arate
    0.66
    Activations Density 0.012%

    No Known Activations