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. 11-RES-JB
    6. 15864
    Prev
    Next
    INDEX
    Explanations

    names and places that seem to be in German

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to names or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prem
    -0.66
     Luffy
    -0.63
     Mayweather
    -0.63
     Bucc
    -0.59
     warrant
    -0.58
     BCC
    -0.58
     Warrant
    -0.58
     whistle
    -0.58
     pokemon
    -0.58
    uously
    -0.56
    POSITIVE LOGITS
    chen
    1.11
    lein
    1.06
    tera
    1.00
    ische
    0.99
    nel
    0.98
    ner
    0.98
    lich
    0.97
    vre
    0.96
    ste
    0.96
    sel
    0.92
    Activations Density 0.084%

    No Known Activations