© 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. 9-RES-JB
    11. 18515
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, specifically referring to sons

    oai_token-act-pair · gpt-3.5-turbo

    references to "son" or familial relationships involving sons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.74
    Union
    -0.73
    Population
    -0.65
    Women
    -0.65
     hazards
    -0.65
     manifold
    -0.61
     conglomer
    -0.58
    Client
    -0.57
     freight
    -0.57
     hazard
    -0.55
    POSITIVE LOGITS
    ogram
    1.00
    nets
    0.98
    hood
    0.97
     Barron
    0.92
     Gohan
    0.86
    ograms
    0.85
    orous
    0.85
    zai
    0.84
    athan
    0.82
    son
    0.82
    Activations Density 0.036%

    No Known Activations