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. 3-RES-JB
    6. 19791
    Prev
    Next
    INDEX
    Explanations

    phrases related to credit ratings and classifications, specifically emphasizing the AAA rating

    oai_token-act-pair · gpt-3.5-turbo

    credit ratings and their respective categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĪ
    -0.78
    inx
    -0.78
     Manson
    -0.78
     Jenner
    -0.76
    ãĥĭ
    -0.75
     Dunham
    -0.73
    stall
    -0.72
    views
    -0.71
    osuke
    -0.71
     Osw
    -0.71
    POSITIVE LOGITS
    ECA
    0.90
    BIL
    0.87
    HHHH
    0.78
    BA
    0.77
    enture
    0.76
     AAA
    0.74
    amily
    0.73
    HE
    0.72
    HL
    0.71
    =]
    0.71
    Activations Density 0.007%

    No Known Activations