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. 18883
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or disputes

    oai_token-act-pair · gpt-3.5-turbo

    the character "ľ"

    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
     hook
    -0.79
     Sammy
    -0.74
     du
    -0.71
     mount
    -0.71
     pyramid
    -0.71
     draw
    -0.71
     Hug
    -0.70
     pigeon
    -0.69
     Lama
    -0.68
     question
    -0.68
    POSITIVE LOGITS
    uthor
    1.32
    ternity
    1.23
    amily
    1.15
    ãĥ´ãĤ¡
    1.07
    cffff
    1.05
    vernment
    1.04
    actual
    0.99
    efe
    0.98
    oil
    0.97
    £
    0.97
    Activations Density 0.153%

    No Known Activations