© 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. 22068
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or objects, especially related to strength or intensity, possibly related to conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "bo" in various contexts, likely denoting a specific action or characteristic

    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
    Interstitial
    -0.86
    ãĥ¼ãĥĨãĤ£
    -0.83
    âķIJ
    -0.78
    UTION
    -0.77
    HCR
    -0.76
     totality
    -0.73
    ãĤ®
    -0.70
    terday
    -0.70
    NESS
    -0.69
     pathway
    -0.68
    POSITIVE LOGITS
    gey
    1.07
    ogie
    1.02
    oby
    0.95
    quet
    0.94
    jo
    0.94
    ambo
    0.94
    zz
    0.92
     bo
    0.92
    agged
    0.88
    onga
    0.87
    Activations Density 0.005%

    No Known Activations