© 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. 11-RES-JB
    11. 9998
    Prev
    Next
    INDEX
    Explanations

    dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wark
    -0.74
    igmatic
    -0.73
    ynchronous
    -0.67
    undle
    -0.65
    obook
    -0.64
    ospital
    -0.63
    formerly
    -0.63
    cussion
    -0.62
     Blasio
    -0.62
    ĸļ
    -0.62
    POSITIVE LOGITS
     ones
    1.46
     setups
    1.33
     pics
    1.30
     things
    1.29
     stuff
    1.29
     spots
    1.20
     places
    1.19
     batches
    1.15
     combos
    1.12
     situations
    1.12
    Activations Density 0.814%

    No Known Activations