© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12130
    Prev
    Next
    INDEX
    Explanations

    sentences starting with an article 'a'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a"

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

    No Comments

    Negative Logits
    Own
    -0.83
    Background
    -0.77
    Contents
    -0.74
    Events
    -0.71
    encies
    -0.68
    bugs
    -0.67
    Listen
    -0.66
    external
    -0.65
    End
    -0.64
    -|
    -0.64
    POSITIVE LOGITS
    rouse
    1.05
    cknowled
    0.94
     hallmark
    0.91
     reminder
    0.86
     handful
    0.85
     spokeswoman
    0.84
     remnant
    0.83
    esthetic
    0.83
     precursor
    0.82
     huge
    0.82
    Activations Density 0.208%

    No Known Activations