© 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. 2084
    Prev
    Next
    INDEX
    Explanations

    commands related to enabling and disabling features or settings

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to enabling and disabling features or settings

    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
    apest
    -1.04
    llah
    -0.87
    axies
    -0.83
    Balt
    -0.81
    代
    -0.77
    rolet
    -0.74
    ĸļ
    -0.73
    itar
    -0.71
    osaurs
    -0.69
    ivan
    -0.69
    POSITIVE LOGITS
     automatic
    0.96
     override
    0.92
     permissions
    0.91
    Disable
    0.91
     toggle
    0.89
     Enabled
    0.89
     defaults
    0.89
     settings
    0.88
    disable
    0.88
     boolean
    0.87
    Activations Density 0.169%

    No Known Activations