© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13452
    Prev
    Next
    INDEX
    Explanations

    references to "raw" materials or elements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "raw" and its variations

    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
    ŃĶ
    -0.91
     Explain
    -0.80
    uyomi
    -0.80
    akeru
    -0.76
    eanor
    -0.76
    onial
    -0.75
    ajo
    -0.73
    ĸļ
    -0.72
    assies
    -0.72
    itism
    -0.71
    POSITIVE LOGITS
    hide
    1.31
     sewage
    0.99
    esome
    0.97
    lings
    0.96
    ls
    0.93
     materials
    0.90
    lins
    0.86
     raw
    0.84
    hest
    0.82
    raw
    0.78
    Activations Density 0.011%

    No Known Activations