© 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. 11-RES-JB
    11. 11192
    Prev
    Next
    INDEX
    Explanations

    instances of self-referential language indicating a group or community of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to collective experiences or group identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ision
    -0.74
    limits
    -0.69
    TEXT
    -0.63
    entanyl
    -0.63
     api
    -0.62
    threat
    -0.60
    Url
    -0.60
    ciation
    -0.60
    ibrary
    -0.58
    tip
    -0.57
    POSITIVE LOGITS
     ourselves
    0.88
     grandparents
    0.79
     fortunate
    0.78
     who
    0.76
     nerds
    0.71
     appreciate
    0.71
    cients
    0.71
     lucky
    0.71
     grew
    0.68
     mortals
    0.68
    Activations Density 0.079%

    No Known Activations