© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 19460
    Prev
    Next
    INDEX
    Explanations

    government-related entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions and oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Invention
    -0.67
    fitting
    -0.57
    font
    -0.57
    taining
    -0.53
    margin
    -0.52
    soType
    -0.52
    asma
    -0.52
     Tags
    -0.52
     sqor
    -0.52
    lighting
    -0.51
    POSITIVE LOGITS
     behaved
    0.98
     cannot
    0.95
     could
    0.94
     would
    0.93
     might
    0.92
     should
    0.92
     got
    0.92
     had
    0.91
     succeeded
    0.89
     hadn
    0.88
    Activations Density 0.730%

    No Known Activations