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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23571
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to violence and injury

    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
    Ö
    -0.56
    emort
    -0.55
    natureconservancy
    -0.54
    {{
    -0.54
    ":[
    -0.51
    OTUS
    -0.50
    eye
    -0.49
    Definition
    -0.49
    Streamer
    -0.49
    \\\\
    -0.49
    POSITIVE LOGITS
     notwithstanding
    0.69
    enegger
    0.62
     unsurprisingly
    0.58
    anting
    0.57
    anwhile
    0.55
     hereby
    0.52
     apologies
    0.52
     respectively
    0.52
     preferably
    0.51
    ãĥ³ãĤ¸
    0.48
    Activations Density 5.505%

    No Known Activations