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. 7-RES-JB
    6. 427
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating superiority or preference

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that express superiority or preference over something else

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eds
    -0.79
    Whe
    -0.73
    ced
    -0.70
    WIND
    -0.70
    whe
    -0.67
    maid
    -0.65
    bender
    -0.64
    992
    -0.64
    Soon
    -0.64
    Italy
    -0.62
    POSITIVE LOGITS
     storing
    0.70
    pex
    0.69
     alternatives
    0.69
     knowing
    0.69
    lihood
    0.68
    uggest
    0.68
     anything
    0.65
    acles
    0.65
     à¨
    0.63
     having
    0.63
    Activations Density 0.215%

    No Known Activations