© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6540
    Prev
    Next
    INDEX
    Explanations

    words related to explosives or dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTION
    -0.86
    ãĥ¼ãĥĨãĤ£
    -0.77
    HCR
    -0.76
    Interstitial
    -0.75
    âķIJ
    -0.74
    rity
    -0.73
    âĶģ
    -0.70
     Sons
    -0.70
     guiActiveUnfocused
    -0.67
    ãĤ»
    -0.67
    POSITIVE LOGITS
     bo
    1.03
    gey
    0.99
    zz
    0.98
    jo
    0.91
    onga
    0.89
    ogie
    0.88
    quet
    0.86
    oby
    0.86
    ambo
    0.83
    etooth
    0.80
    Activations Density 0.007%

    No Known Activations