© 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. 3050
    Prev
    Next
    INDEX
    Explanations

    phrases related to verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but."

    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
    achus
    -0.88
    andom
    -0.85
    ISO
    -0.84
    Ô
    -0.83
    assment
    -0.74
    aux
    -0.72
    llah
    -0.72
    \\\\
    -0.71
    =]
    -0.71
    elf
    -0.70
    POSITIVE LOGITS
    oshenko
    0.72
     wig
    0.70
     logo
    0.68
     molded
    0.64
     prone
    0.63
     translator
    0.63
     patch
    0.63
     PA
    0.62
     addon
    0.61
     knit
    0.61
    Activations Density 0.000%

    No Known Activations