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. 15089
    Prev
    Next
    INDEX
    Explanations

    words related to levels or heights, particularly with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to airborne military operations and environmental impacts

    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
     Marketable
    -0.89
    esson
    -0.77
     Rica
    -0.68
     McKenna
    -0.67
     Sawyer
    -0.67
     Norris
    -0.66
     Compass
    -0.66
    herty
    -0.65
     Issa
    -0.64
     ABE
    -0.63
    POSITIVE LOGITS
    based
    1.23
    level
    1.03
    floor
    1.02
    condition
    1.00
    saving
    1.00
    sensitive
    0.98
    mounted
    0.98
    surface
    0.97
    brew
    0.97
    oriented
    0.96
    Activations Density 0.092%

    No Known Activations