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. 11-RES-JB
    6. 15612
    Prev
    Next
    INDEX
    Explanations

    phonetic similarities or wordplay, especially with repetitive patterns or sounds

    oai_token-act-pair · gpt-3.5-turbo

    complex interactions involving medical conditions and character development

    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
    rition
    -0.93
    tsky
    -0.78
    oric
    -0.71
    xual
    -0.71
    ¬¼
    -0.69
    igers
    -0.68
    481
    -0.67
    iversary
    -0.67
    worms
    -0.66
    inger
    -0.66
    POSITIVE LOGITS
     Far
    2.30
    Far
    2.29
    far
    1.88
     FAR
    1.64
     far
    1.45
     Near
    1.15
    hest
    1.10
    near
    1.08
     farther
    1.06
    Near
    1.06
    Activations Density 0.162%

    No Known Activations