© 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. 23659
    Prev
    Next
    INDEX
    Explanations

    actions described in the form "As you can see"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or observation

    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
    oleon
    -0.75
    pan
    -0.72
    rang
    -0.70
    lam
    -0.69
    istries
    -0.67
    anmar
    -0.65
    ocaly
    -0.64
    addons
    -0.64
     Deng
    -0.63
    wcs
    -0.63
    POSITIVE LOGITS
    âĶĢ
    0.72
    ees
    0.71
     deduction
    0.70
    terday
    0.69
     (),
    0.69
     anecd
    0.63
    ,.
    0.61
    .—
    0.60
    UME
    0.60
    ,—
    0.60
    Activations Density 0.071%

    No Known Activations