© 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 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. 10-RES-JB
    11. 16640
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    themes of accountability and personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.83
    ellen
    -0.82
    atown
    -0.78
    alyst
    -0.78
    ibaba
    -0.77
     GOODMAN
    -0.72
    wang
    -0.70
    paces
    -0.67
    yip
    -0.65
     sidx
    -0.65
    POSITIVE LOGITS
     sins
    1.63
     mistakes
    1.58
     inaction
    1.58
     actions
    1.53
     failings
    1.52
     transgress
    1.47
     failures
    1.40
     negligence
    1.39
     wrongdoing
    1.36
     crimes
    1.36
    Activations Density 0.361%

    No Known Activations