© 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. 7191
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular person with a last name starting with "Kl" and ending with "ump."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Klump" and its variants in various contexts

    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
    EMENT
    -0.82
    ãĥ¼ãĥĨãĤ£
    -0.77
    ITED
    -0.76
    ãģ®éŃĶ
    -0.75
    ELY
    -0.74
    CLASSIFIED
    -0.74
    ãģ¦
    -0.72
    LEASE
    -0.71
    llah
    -0.70
    POSITIVE LOGITS
    assic
    1.06
     Klux
    1.00
    itsch
    0.99
    adium
    0.96
    avier
    0.96
    oser
    0.94
    utz
    0.91
    icker
    0.90
    azo
    0.88
    azy
    0.86
    Activations Density 0.004%

    No Known Activations