© 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. 1605
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" that are preceded by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "a"

    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
    Edit
    -0.78
    Contents
    -0.71
    Orig
    -0.68
    evidence
    -0.68
    Hon
    -0.67
    Events
    -0.66
    Links
    -0.66
    ATURES
    -0.66
    enance
    -0.66
     Jagu
    -0.64
    POSITIVE LOGITS
     lot
    1.17
     bunch
    1.11
     handful
    1.04
    rouse
    1.03
     huge
    1.03
     few
    0.97
     couple
    0.96
     massive
    0.94
     plethora
    0.93
     sizable
    0.93
    Activations Density 1.043%

    No Known Activations