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. 9-RES-JB
    6. 5132
    Prev
    Next
    INDEX
    Explanations

    email address entry prompts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Enter" or phrases indicating user input or interaction prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utsche
    -0.64
    unks
    -0.62
     gunned
    -0.60
    ework
    -0.60
     Bulletin
    -0.59
    packs
    -0.58
     battered
    -0.58
    ucket
    -0.57
    aimon
    -0.57
     Singer
    -0.56
    POSITIVE LOGITS
    prise
    1.76
    tainment
    1.64
    prising
    1.59
    prises
    1.59
    tain
    1.49
    taining
    1.45
    tained
    1.13
    TAIN
    1.05
    ococ
    0.90
    tains
    0.87
    Activations Density 0.031%

    No Known Activations