© 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. 9-RES-JB
    11. 5471
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and technical concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data and references to publications or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unquestion
    -0.58
     every
    -0.58
     hardly
    -0.57
     relentlessly
    -0.55
     scarcely
    -0.55
     insidious
    -0.54
     altogether
    -0.54
     anyone
    -0.54
     everyone
    -0.54
     untold
    -0.53
    POSITIVE LOGITS
    odium
    0.66
    GV
    0.62
    nesota
    0.60
    odox
    0.58
    soType
    0.56
    senal
    0.55
    ofi
    0.53
    ngth
    0.52
    kos
    0.51
    united
    0.51
    Activations Density 1.130%

    No Known Activations