© 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. 7-RES-JB
    11. 8655
    Prev
    Next
    INDEX
    Explanations

    details related to financial and economic aspects, especially pertaining to concerns such as wealth, budgeting, and financial capital

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions or phrases linked by "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.91
    WARD
    -0.77
    advertising
    -0.75
    ãĥŁ
    -0.72
    ãĥ³ãĤ¸
    -0.71
    ãĥī
    -0.70
    usk
    -0.68
    å°Ĩ
    -0.68
    atre
    -0.68
    ãĤ¯
    -0.68
    POSITIVE LOGITS
     knack
    0.89
     ceilings
    0.71
     aspirations
    0.71
     balances
    0.70
     capability
    0.69
     equivalents
    0.68
     ceiling
    0.68
     ambitions
    0.68
     purse
    0.68
     penchant
    0.66
    Activations Density 0.551%

    No Known Activations