© 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. 6208
    Prev
    Next
    INDEX
    Explanations

    terms related to chemicals or substances that have an effect on the brain or body

    oai_token-act-pair · gpt-3.5-turbo

    words related to activity levels, particularly in a regulatory or clinical context

    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
    adra
    -0.86
    Ń·
    -0.79
    ľ
    -0.73
    ħ
    -0.73
    ĺħ
    -0.72
    «ĺ
    -0.72
    ©¶æ
    -0.70
    hner
    -0.70
    è£ħ
    -0.68
    ĨĴ
    -0.67
    POSITIVE LOGITS
    active
    0.94
    ibility
    0.88
    terday
    0.82
    ãĤ¿
    0.82
    imental
    0.81
    arial
    0.75
    action
    0.72
    uary
    0.70
    activity
    0.69
     ingredient
    0.69
    Activations Density 0.010%

    No Known Activations