© 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. 7-RES-JB
    11. 20772
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with Brazilian political figures and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ding
    -0.74
     Illum
    -0.68
    ISH
    -0.68
    nery
    -0.66
    ned
    -0.66
    ded
    -0.65
     Shed
    -0.62
     Frankenstein
    -0.61
     guiActiveUnfocused
    -0.60
    incible
    -0.60
    POSITIVE LOGITS
    ĵ
    1.07
    ignty
    1.00
    £
    0.95
    §
    0.95
    irie
    0.94
    ¨
    0.94
    lete
    0.93
    zza
    0.93
    ķ
    0.93
    opard
    0.91
    Activations Density 0.053%

    No Known Activations