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

    Neuronpedia

    Jacobian LensNEW
    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. 1168
    Prev
    Next
    INDEX
    Explanations

    mentions of technology or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'K'

    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
    terday
    -0.72
    wcsstore
    -0.70
    phrine
    -0.66
     adversity
    -0.66
    quist
    -0.64
     mosqu
    -0.64
     contraceptives
    -0.63
    zona
    -0.62
     diapers
    -0.60
    purpose
    -0.60
    POSITIVE LOGITS
    won
    0.98
    EEP
    0.97
    ernel
    0.96
    rieg
    0.93
    orea
    0.92
    eeper
    0.91
    laus
    0.91
    ISS
    0.90
    istani
    0.89
    irk
    0.88
    Activations Density 0.020%

    No Known Activations