© 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. 2-RES-JB
    6. 18537
    Prev
    Next
    INDEX
    Explanations

    instances where a specific event or action is mentioned as being done at a particular location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at"

    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
    gravity
    -0.87
    FTWARE
    -0.82
    alpha
    -0.75
    Russ
    -0.67
    fill
    -0.65
    glass
    -0.64
    Lens
    -0.63
    worthiness
    -0.63
    monary
    -0.63
    REDACTED
    -0.61
    POSITIVE LOGITS
     least
    1.30
    abase
    0.94
     halftime
    0.91
    onement
    0.90
    roph
    0.80
    hens
    0.78
     liberty
    0.77
     weekends
    0.77
    rial
    0.76
     variance
    0.75
    Activations Density 0.234%

    No Known Activations