© 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. 2-RES-JB
    11. 17567
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "supported."

    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
    oufl
    -0.76
    kay
    -0.75
     Hebdo
    -0.73
    opers
    -0.73
    azard
    -0.71
    ldom
    -0.71
    hunt
    -0.71
    odor
    -0.70
    thur
    -0.69
    blem
    -0.68
    POSITIVE LOGITS
     supported
    0.99
     Supported
    0.93
     Supports
    0.91
     supports
    0.83
     supporting
    0.81
    Supported
    0.78
     Supporting
    0.76
    iary
    0.75
    supported
    0.75
     corrobor
    0.73
    Activations Density 0.024%

    No Known Activations