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. 21936
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms related to various subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, physical attributes, and systems in a structured context

    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
    hops
    -0.70
     Machines
    -0.69
     establishments
    -0.69
     Vehicles
    -0.68
    units
    -0.66
    lees
    -0.65
    rencies
    -0.64
    events
    -0.64
    casts
    -0.63
    urrencies
    -0.62
    POSITIVE LOGITS
     version
    0.77
     standpoint
    0.77
     variant
    0.69
     statement
    0.69
     arrangement
    0.68
     perspective
    0.67
     timetable
    0.67
     injunction
    0.67
     dose
    0.67
     attitude
    0.65
    Activations Density 1.003%

    No Known Activations