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. 4-RES-JB
    6. 18258
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly the name "Calvin."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Calvin" and related derivatives in various contexts

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

    No Comments

    Negative Logits
    IRE
    -0.80
    igating
    -0.75
    innie
    -0.72
    igation
    -0.72
    ochond
    -0.69
    ebin
    -0.68
    IRED
    -0.68
    ramid
    -0.68
    eals
    -0.67
    yip
    -0.67
    POSITIVE LOGITS
     Calvin
    0.90
     Bacon
    0.81
     Klein
    0.79
    istic
    0.77
    istically
    0.77
     Staples
    0.74
    icum
    0.70
     Cool
    0.69
     Hayden
    0.69
    son
    0.68
    Activations Density 0.011%

    No Known Activations