Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19567
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "McKenna"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jenna" and terms related to cockpit situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IGF
    -0.70
     delinquent
    -0.68
    ary
    -0.65
     bookstore
    -0.64
     Marxism
    -0.61
     behav
    -0.60
     Clicker
    -0.60
     extremism
    -0.59
     Marxist
    -0.58
     delinqu
    -0.58
    POSITIVE LOGITS
    issions
    1.04
    enna
    0.99
    opol
    0.94
    issance
    0.91
    thia
    0.90
    iets
    0.86
    iership
    0.85
    obyl
    0.83
     Jenna
    0.82
    onite
    0.82
    Activations Density 0.015%

    No Known Activations