© 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. 1658
    Prev
    Next
    INDEX
    Explanations

    mentions of family members, specifically uncles and aunts

    oai_token-act-pair · gpt-3.5-turbo

    references to family members, particularly uncles and aunts

    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
    mberg
    -0.80
    isers
    -0.71
    EVA
    -0.70
    pb
    -0.70
    veyard
    -0.67
     lapse
    -0.67
    istas
    -0.64
    acters
    -0.64
    istically
    -0.62
    pless
    -0.59
    POSITIVE LOGITS
     uncle
    0.98
    liest
    0.89
    hest
    0.89
     nephew
    0.89
    aned
    0.84
     Vernon
    0.84
    hetically
    0.81
    aleb
    0.81
    rieved
    0.79
     niece
    0.79
    Activations Density 0.052%

    No Known Activations