© 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. 4-RES-JB
    11. 20823
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word 'Naz'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Naz."

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

    No Comments

    Negative Logits
    ACTED
    -0.75
    #$
    -0.74
    IVES
    -0.73
    lessly
    -0.72
    ENGTH
    -0.71
     boiling
    -0.66
    ESSION
    -0.66
    tenance
    -0.65
    IVE
    -0.64
    OME
    -0.64
    POSITIVE LOGITS
    areth
    1.18
    ril
    1.00
    Naz
    1.00
    aji
    0.98
    imet
    0.97
    oche
    0.96
    emonic
    0.91
    anas
    0.90
    oid
    0.88
    ollah
    0.87
    Activations Density 0.005%

    No Known Activations