© 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. 6-RES-JB
    11. 15030
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically homes

    oai_token-act-pair · gpt-3.5-turbo

    references to homes or residential locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andum
    -0.86
    uality
    -0.71
    ãģĨ
    -0.67
     guides
    -0.66
    rencies
    -0.66
    imester
    -0.64
     patience
    -0.62
    ussian
    -0.62
    auts
    -0.62
    irements
    -0.62
    POSITIVE LOGITS
    owner
    0.89
    wife
    0.88
    nikov
    0.88
    chool
    0.86
    stead
    0.86
    coming
    0.81
     burglary
    0.81
    yard
    0.80
    broken
    0.78
     occupant
    0.78
    Activations Density 0.074%

    No Known Activations