© 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. 7-RES-JB
    11. 23632
    Prev
    Next
    INDEX
    Explanations

    phrases related to operations or operational tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to operational concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esville
    -0.76
    eree
    -0.75
    fix
    -0.72
    hens
    -0.70
    uran
    -0.70
    iard
    -0.69
    eger
    -0.66
     Ceres
    -0.64
    âĶģ
    -0.64
    marks
    -0.64
    POSITIVE LOGITS
    aquin
    0.90
    FTWARE
    0.80
    acion
    0.76
    atic
    0.75
    merce
    0.73
    ament
    0.71
    ————————
    0.69
    andi
    0.67
    rett
    0.67
    ufact
    0.65
    Activations Density 0.035%

    No Known Activations