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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 23535
    Prev
    Next
    INDEX
    Explanations

    Italian last names

    oai_token-act-pair · gpt-3.5-turbo

    specific names or identifiers from various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPS
    -0.64
     dime
    -0.61
     fluor
    -0.58
     satell
    -0.57
     differential
    -0.56
     flock
    -0.55
    ¿½
    -0.55
    hyde
    -0.55
    ãĤ´ãĥ³
    -0.54
     inequ
    -0.53
    POSITIVE LOGITS
    andise
    1.01
    uay
    0.90
    ultural
    0.89
    iani
    0.88
    orno
    0.87
    vernment
    0.83
    utra
    0.81
    iano
    0.78
    ribune
    0.77
    ierrez
    0.77
    Activations Density 0.175%

    No Known Activations