© 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. 11-RES-JB
    11. 4757
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding significant events or actions involving organizations and their outcomes

    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
     classmates
    -0.77
     teammate
    -0.69
     solitude
    -0.68
     exchanged
    -0.66
    ertility
    -0.65
     fellow
    -0.60
     recounted
    -0.60
    avorite
    -0.60
     teammates
    -0.60
     compat
    -0.60
    POSITIVE LOGITS
    Its
    0.90
    erity
    0.88
     incompetence
    0.80
     bung
    0.79
     meddling
    0.78
     enforcing
    0.77
     Its
    0.77
     incompet
    0.77
     inept
    0.75
     incompetent
    0.75
    Activations Density 0.759%

    No Known Activations