Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24371
    Prev
    Next
    INDEX
    Explanations

    words related to financial matters or transactions

    oai_token-act-pair · gpt-3.5-turbo

    words related to financial terms and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Addiction
    -0.74
     prolific
    -0.72
     Carpenter
    -0.72
    cycle
    -0.72
     Aval
    -0.71
    ories
    -0.71
    camp
    -0.70
     Lyons
    -0.69
    leys
    -0.68
     Weed
    -0.68
    POSITIVE LOGITS
     fin
    3.38
     fins
    1.72
    fin
    1.29
    Fin
    1.10
     Elon
    1.09
     chore
    1.09
     stra
    1.04
     jer
    1.04
     fu
    1.04
     kin
    0.98
    Activations Density 0.016%

    No Known Activations