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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 12210
    Prev
    Next
    INDEX
    Explanations

    terms related to legal documents, arrests, and government agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to official immigration and citizenship processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zinski
    -0.63
    imb
    -0.62
    hare
    -0.60
    yss
    -0.59
    gif
    -0.59
    amaz
    -0.59
    emonium
    -0.57
    boxing
    -0.57
    onding
    -0.56
    unic
    -0.56
    POSITIVE LOGITS
    SEA
    0.62
    kus
    0.60
    ISA
    0.58
     certainty
    0.55
     sciences
    0.54
     prol
    0.53
     prestigious
    0.52
     protections
    0.52
     Guinness
    0.51
    ©¶æ¥µ
    0.51
    Activations Density 1.288%

    No Known Activations