© 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. 2-RES-JB
    11. 17811
    Prev
    Next
    INDEX
    Explanations

    instances related to the concept of money or cash

    oai_token-act-pair · gpt-3.5-turbo

    mentions of financial transactions or currency, particularly cash-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå
    -0.75
    obia
    -0.74
    ARGET
    -0.71
    ROR
    -0.70
    OOL
    -0.69
    £ı
    -0.65
    ¢
    -0.64
    éĥ
    -0.64
    advertisement
    -0.63
    IJ
    -0.63
    POSITIVE LOGITS
    mere
    0.96
    more
    0.84
     Cash
    0.84
    Cash
    0.79
    eno
    0.78
    fields
    0.77
    nuts
    0.74
    rencies
    0.73
    hers
    0.72
    eteria
    0.71
    Activations Density 0.006%

    No Known Activations