© 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. 1-RES-JB
    6. 12930
    Prev
    Next
    INDEX
    Explanations

    detailed analyses or reviews denoted by the term "in-depth."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of depth or thoroughness in analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anza
    -0.69
    Bey
    -0.68
    hett
    -0.65
    ifiable
    -0.63
    avis
    -0.63
    asel
    -0.62
    abad
    -0.60
    zzi
    -0.60
     Sabha
    -0.59
     NCT
    -0.59
    POSITIVE LOGITS
    depth
    1.48
     depth
    0.97
     Depth
    0.97
    Depth
    0.92
    colour
    0.83
     penetration
    0.80
    vier
    0.78
    xit
    0.76
    xual
    0.75
     confir
    0.72
    Activations Density 0.005%

    No Known Activations