© 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. 17467
    Prev
    Next
    INDEX
    Explanations

    mentions of people or social interactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "People" in various contexts

    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
    NES
    -0.81
     srfAttach
    -0.78
    SET
    -0.74
    COMPLE
    -0.72
    ITAL
    -0.70
    etric
    -0.70
     Lank
    -0.70
    SPONSORED
    -0.69
    enegger
    -0.68
    Material
    -0.67
    POSITIVE LOGITS
     smugglers
    1.02
    folk
    0.88
     who
    0.73
     born
    0.72
    hate
    0.68
    incerity
    0.68
     starve
    0.67
    bably
    0.66
     mourning
    0.66
     traffickers
    0.65
    Activations Density 0.097%

    No Known Activations