© 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. 18623
    Prev
    Next
    INDEX
    Explanations

    terms related to financial capital and taxes

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to capital and capital gains

    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
    api
    -0.71
    ller
    -0.70
     Schr
    -0.69
    £ı
    -0.69
    DEN
    -0.68
    unction
    -0.68
    ï¸
    -0.66
    lder
    -0.65
     Moj
    -0.63
    tto
    -0.63
    POSITIVE LOGITS
    istic
    1.05
    ization
    1.04
    izing
    1.02
     gains
    1.01
    ising
    0.98
    isation
    0.96
    ized
    0.96
    izations
    0.95
    izes
    0.94
     accumulation
    0.93
    Activations Density 0.035%

    No Known Activations