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. 7-RES-JB
    6. 22153
    Prev
    Next
    INDEX
    Explanations

    terms related to ingredients or components in experimental studies, such as fat, glucose, protein, and drinks

    oai_token-act-pair · gpt-3.5-turbo

    information related to health and dietary impacts on individuals

    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
    NetMessage
    -0.73
    redo
    -0.68
    Ireland
    -0.67
     EntityItem
    -0.66
    "}],"
    -0.66
     compan
    -0.66
    deal
    -0.65
     Cabin
    -0.65
     unic
    -0.64
    ================================================================
    -0.64
    POSITIVE LOGITS
     placebo
    1.06
     âμ
    1.02
     simulated
    0.96
     randomly
    0.95
     randomized
    0.92
     Experiment
    0.90
     experiment
    0.87
     participants
    0.87
     MRI
    0.86
     questionnaire
    0.85
    Activations Density 0.577%

    No Known Activations