© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 9986
    Prev
    Next
    INDEX
    Explanations

    financial institutions, particularly Moody's

    oai_token-act-pair · gpt-3.5-turbo

    references to the credit rating agency Moody's

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protocol
    -0.84
    aus
    -0.70
     conquest
    -0.69
     jihad
    -0.69
     prot
    -0.68
     tile
    -0.68
     colonization
    -0.67
    gal
    -0.67
     apps
    -0.64
    ourn
    -0.64
    POSITIVE LOGITS
     Moody
    4.39
     CBO
    1.29
    agall
    1.18
     Nielsen
    1.12
     Mub
    1.12
     Moff
    1.08
     Mood
    1.06
     Malfoy
    1.04
     Piper
    1.04
     Miz
    1.04
    Activations Density 0.032%

    No Known Activations