© 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. 6-RES-JB
    11. 14898
    Prev
    Next
    INDEX
    Explanations

    words related to political and economic news

    oai_token-act-pair · gpt-3.5-turbo

    topics related to financial and economic challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totaled
    -0.73
    kees
    -0.71
     cough
    -0.70
     honors
    -0.70
    zona
    -0.68
     capitalize
    -0.68
     totaling
    -0.67
     traveling
    -0.67
    boro
    -0.66
     dime
    -0.66
    POSITIVE LOGITS
    Labour
    1.09
    Britain
    1.08
    England
    1.07
    Shape
    1.01
    Article
    1.01
    Scotland
    0.97
    gow
    0.89
    BBC
    0.86
     mould
    0.85
    Writing
    0.85
    Activations Density 0.549%

    No Known Activations