© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2000
    Prev
    Next
    INDEX
    Explanations

    phrases related to denial or deprivation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to denial and deprivation

    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
    Fail
    -0.73
    wcsstore
    -0.73
     Images
    -0.73
    lich
    -0.72
    rather
    -0.69
    flies
    -0.68
     Tycoon
    -0.68
    inventoryQuantity
    -0.65
    cycl
    -0.65
     Sins
    -0.63
    POSITIVE LOGITS
     citizenship
    0.99
     access
    0.95
     opportunities
    0.91
     privileges
    0.89
     permission
    0.88
     entry
    0.83
     accessing
    0.83
     visas
    0.81
     accommodations
    0.80
     opportunity
    0.80
    Activations Density 0.153%

    No Known Activations