© 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. 7-RES-JB
    11. 21471
    Prev
    Next
    INDEX
    Explanations

    phrases related to government, politics, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and significant entities

    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
    fitting
    -0.56
    rising
    -0.56
    foundland
    -0.55
     Invention
    -0.55
    taining
    -0.53
     aback
    -0.53
     Huh
    -0.53
    etheless
    -0.52
     Velocity
    -0.52
     Brunswick
    -0.51
    POSITIVE LOGITS
     could
    0.87
     might
    0.83
     cannot
    0.83
     had
    0.81
     got
    0.81
     should
    0.81
     would
    0.80
     went
    0.80
     will
    0.78
     can
    0.78
    Activations Density 0.806%

    No Known Activations