© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5594
    Prev
    Next
    INDEX
    Explanations

    references to the entity or concept "Moloch"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "molestation" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rampage
    -0.66
     laureate
    -0.61
    Foot
    -0.60
     depreciation
    -0.60
     Repair
    -0.59
    --------------
    -0.56
    Round
    -0.56
     Siege
    -0.56
     frontrunner
    -0.55
     apost
    -0.55
    POSITIVE LOGITS
    estation
    1.38
    asses
    1.20
    ossus
    1.18
    esting
    1.12
    onel
    0.99
    oton
    0.99
    ested
    0.98
    ten
    0.97
    okia
    0.96
    esta
    0.96
    Activations Density 0.038%

    No Known Activations