© 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. 4-RES-JB
    11. 10154
    Prev
    Next
    INDEX
    Explanations

    references to financial amounts in euros

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary amounts in euros

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

    No Comments

    Negative Logits
     Peb
    -0.72
    Discussion
    -0.71
     Sioux
    -0.70
    eer
    -0.70
     Boards
    -0.68
     Flavoring
    -0.68
     Iro
    -0.65
     Ivy
    -0.65
     Siber
    -0.65
     thumbnail
    -0.64
    POSITIVE LOGITS
     âĤ¬
    0.92
     (£
    0.91
    âĤ¬
    0.89
     euros
    0.86
     ($
    0.86
    imeter
    0.79
     sterling
    0.77
    akis
    0.75
    umen
    0.70
    cow
    0.70
    Activations Density 0.007%

    No Known Activations