© 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. 9918
    Prev
    Next
    INDEX
    Explanations

    terms related to tax

    oai_token-act-pair · gpt-3.5-turbo

    references to tax-related topics and terms

    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
     Watts
    -0.72
    Ò
    -0.65
     Osw
    -0.64
     Ange
    -0.63
     Sadd
    -0.63
    lihood
    -0.61
     Yug
    -0.61
     sshd
    -0.60
     Wynne
    -0.60
     ANGEL
    -0.59
    POSITIVE LOGITS
    payer
    1.35
    payers
    1.26
    onomy
    1.23
    onomic
    1.21
    onom
    1.07
     evasion
    1.03
     havens
    1.01
    ider
    1.00
    paying
    0.98
     deductible
    0.93
    Activations Density 0.044%

    No Known Activations