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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4402
    Prev
    Next
    INDEX
    Explanations

    number figures related to monetary values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to financial amounts or monetary transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etary
    -0.92
    ufact
    -0.89
    joined
    -0.82
    naissance
    -0.81
    emark
    -0.78
    staking
    -0.78
    chers
    -0.75
    puter
    -0.74
    ple
    -0.74
    osite
    -0.74
    POSITIVE LOGITS
     rods
    1.09
    407
    0.83
    ãĤĮ
    0.80
    507
    0.78
    402
    0.78
    553
    0.78
    018
    0.76
    58
    0.75
    403
    0.74
    405
    0.74
    Activations Density 0.029%

    No Known Activations