© 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. 18912
    Prev
    Next
    INDEX
    Explanations

    references to historical events or time periods

    oai_token-act-pair · gpt-3.5-turbo

    frequent references to the term "Great" in historical or economic contexts

    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
    qqa
    -0.85
    ograp
    -0.81
    ople
    -0.79
    utical
    -0.78
    Ãį
    -0.71
    clips
    -0.70
    isSpecialOrderable
    -0.70
    Downloadha
    -0.70
    earchers
    -0.69
    istry
    -0.68
    POSITIVE LOGITS
    batch
    0.92
    ness
    0.91
     Recession
    0.90
     Basin
    0.83
     Divide
    0.83
     Lakes
    0.83
     strides
    0.81
     Barrier
    0.79
    sword
    0.79
     Falls
    0.77
    Activations Density 0.018%

    No Known Activations