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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11461
    Prev
    Next
    INDEX
    Explanations

    mentions of people taking actions in response to events or expressing opinions on social platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to actions taken by individuals or groups, particularly in the context of social or political activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGS
    -0.71
    CLASSIFIED
    -0.70
    afia
    -0.68
    ements
    -0.64
    ablishment
    -0.64
    ascript
    -0.62
    /-
    -0.61
    glomer
    -0.61
    ativity
    -0.58
    don
    -0.58
    POSITIVE LOGITS
     twitter
    0.91
     Twitter
    0.86
    pless
    0.82
     Facebook
    0.76
    amph
    0.74
     social
    0.72
     Instagram
    0.71
     forums
    0.71
    umblr
    0.70
     stride
    0.69
    Activations Density 0.052%

    No Known Activations