© 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. 10-RES-JB
    11. 20438
    Prev
    Next
    INDEX
    Explanations

    number-related information, specifically monetary values

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary figures and amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acid
    -0.81
    anism
    -0.78
    agree
    -0.76
     ate
    -0.72
    enemy
    -0.71
    empty
    -0.68
     ie
    -0.67
    ache
    -0.67
    abuse
    -0.67
    Americans
    -0.66
    POSITIVE LOGITS
     new
    1.34
     slew
    1.27
     redesigned
    1.14
     revamped
    1.14
     revised
    1.06
     plethora
    1.06
     handful
    1.02
     whopping
    1.00
     raft
    0.99
     partnership
    0.97
    Activations Density 0.301%

    No Known Activations