© 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. 2-RES-JB
    11. 23307
    Prev
    Next
    INDEX
    Explanations

    references to the term "Raw" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Raw"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.88
    uated
    -0.84
    uate
    -0.83
    mercial
    -0.78
    akeru
    -0.75
    raints
    -0.75
    ortium
    -0.74
    eanor
    -0.73
    llor
    -0.73
    ateral
    -0.73
    POSITIVE LOGITS
    lings
    1.10
    Raw
    1.03
    ls
    1.02
    hide
    1.01
    lins
    0.97
    esome
    0.92
    kus
    0.83
    Skin
    0.80
     RAW
    0.79
    raw
    0.78
    Activations Density 0.003%

    No Known Activations