© 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. 7553
    Prev
    Next
    INDEX
    Explanations

    words related to education and intellectual development

    oai_token-act-pair · gpt-3.5-turbo

    references to elevated standards or levels in various contexts

    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
     Paraly
    -0.70
     Sho
    -0.69
    bers
    -0.66
     Scythe
    -0.64
     Monstrous
    -0.63
    pty
    -0.63
     Shin
    -0.62
    icate
    -0.61
     vanquished
    -0.61
     Ramadan
    -0.59
    POSITIVE LOGITS
     than
    1.02
    than
    1.00
     referen
    0.86
     tiers
    0.86
    iating
    0.85
     pitched
    0.84
     priced
    0.81
     levels
    0.80
    lighting
    0.80
    reek
    0.77
    Activations Density 0.024%

    No Known Activations