© 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. 1-RES-JB
    6. 3284
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Hen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of the name "Henrik"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ε
    -0.72
    terday
    -0.71
    ULT
    -0.70
    ERROR
    -0.69
    ι
    -0.68
    Sax
    -0.68
    Wide
    -0.64
    ãĥķãĤ©
    -0.62
    Reference
    -0.62
    Examples
    -0.61
    POSITIVE LOGITS
    rique
    1.26
    ning
    0.97
     Hen
    0.97
    rette
    0.95
    lein
    0.95
    riks
    0.95
    etr
    0.91
    riet
    0.89
    emy
    0.87
    ricks
    0.86
    Activations Density 0.007%

    No Known Activations