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. 22071
    Prev
    Next
    INDEX
    Explanations

    conditions or actions related to ownership, accomplishment, service, and wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    activities and states related to ownership and experience

    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
    audi
    -0.62
     furious
    -0.62
    Australia
    -0.61
    RB
    -0.60
     Cohn
    -0.60
    Ranked
    -0.60
    Bah
    -0.60
    ansky
    -0.60
    NL
    -0.59
    IPS
    -0.59
    POSITIVE LOGITS
     previously
    0.84
     sufficiently
    0.83
     previous
    0.80
     Entered
    0.77
    /-
    0.73
     preceding
    0.70
    ufact
    0.69
     hitherto
    0.67
     thereto
    0.67
     conquer
    0.67
    Activations Density 0.477%

    No Known Activations