© 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. 7-RES-JB
    11. 5749
    Prev
    Next
    INDEX
    Explanations

    terms related to attracting people or things, particularly from different regions or countries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recruitment or attracting individuals, particularly in the context of jihadism and immigration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknow
    -0.72
     PBS
    -0.68
     Wem
    -0.67
     repealed
    -0.65
     protocol
    -0.64
     corrected
    -0.62
     Judicial
    -0.62
    saf
    -0.61
     ellipt
    -0.61
     FDR
    -0.60
    POSITIVE LOGITS
     congreg
    0.85
    ships
    0.80
    umni
    0.80
     opportunities
    0.78
     entrants
    0.78
     overseas
    0.78
     abroad
    0.77
    entry
    0.76
     lured
    0.75
     visas
    0.75
    Activations Density 0.587%

    No Known Activations