© 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. 10046
    Prev
    Next
    INDEX
    Explanations

    family relationships or family-related terms, particularly focusing on parent-child relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in incidents, particularly in a legal or distressing context

    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
    izoph
    -0.72
    raltar
    -0.66
    peed
    -0.65
    ichick
    -0.64
    åĮ
    -0.62
    bes
    -0.62
    pell
    -0.61
    orting
    -0.60
    spons
    -0.60
    OME
    -0.60
    POSITIVE LOGITS
    's
    0.98
     fled
    0.89
     suffered
    0.88
     surn
    0.88
     died
    0.87
     belonged
    0.86
     was
    0.85
     testified
    0.85
     awoke
    0.82
     withdrew
    0.82
    Activations Density 0.146%

    No Known Activations