© 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. 19292
    Prev
    Next
    INDEX
    Explanations

    phrases indicating blame or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to personal accountability and blame

    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
    iolet
    -0.80
    atform
    -0.80
    ago
    -0.74
    atos
    -0.72
    ISTER
    -0.72
    chedel
    -0.72
    xon
    -0.70
    weeney
    -0.69
    CHO
    -0.69
    ctica
    -0.69
    POSITIVE LOGITS
    lessly
    0.96
    lessness
    0.75
     fault
    0.74
    less
    0.74
    ously
    0.72
     forgiven
    0.71
     Karma
    0.68
    errors
    0.68
     motive
    0.67
    saf
    0.66
    Activations Density 0.024%

    No Known Activations