© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20278
    Prev
    Next
    INDEX
    Explanations

    the name "Mik" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Mik" and "Mog" within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proper
    -0.72
     Crescent
    -0.65
    istics
    -0.64
     equivalents
    -0.62
     Times
    -0.62
     checkout
    -0.61
    erie
    -0.61
     Paradox
    -0.61
     Dispatch
    -0.60
     Nordic
    -0.60
    POSITIVE LOGITS
    adish
    1.19
    eki
    1.07
    tab
    1.07
    htar
    1.06
    enzie
    1.05
    ullah
    1.03
    uls
    1.00
    ael
    1.00
    ako
    0.99
    nih
    0.99
    Activations Density 0.031%

    No Known Activations