© 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. 2-RES-JB
    11. 12468
    Prev
    Next
    INDEX
    Explanations

    terms related to the Ku Klux Klan or racist ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms associated with notable historical or cultural 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
    pection
    -0.84
     hars
    -0.68
     NEC
    -0.68
     Finder
    -0.67
     datas
    -0.65
    fires
    -0.63
    claw
    -0.59
     holiest
    -0.59
    FG
    -0.58
     Kraken
    -0.58
    POSITIVE LOGITS
    sburgh
    0.93
    nih
    0.86
    osate
    0.72
    roleum
    0.72
    åĬ
    0.69
    affer
    0.69
    irus
    0.69
    \":
    0.69
    sylvania
    0.69
    assium
    0.69
    Activations Density 0.037%

    No Known Activations