© 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. 15756
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms associated with rules, guidelines, and metrics

    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
     Shed
    -0.74
    arnaev
    -0.72
    ream
    -0.68
    aughters
    -0.65
    zl
    -0.62
    grave
    -0.60
    etsk
    -0.60
     Somers
    -0.60
    iland
    -0.59
    pload
    -0.57
    POSITIVE LOGITS
     fame
    0.70
    ³³³
    0.70
    bows
    0.68
     syndrome
    0.67
     ---
    0.61
    thood
    0.61
     +++
    0.60
     retard
    0.60
    smanship
    0.60
     communism
    0.60
    Activations Density 0.417%

    No Known Activations