© 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. 11-RES-JB
    6. 3897
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" being emphasized in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it" in various contexts, emphasizing its significance or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.74
    course
    -0.69
    asa
    -0.60
     Warranty
    -0.59
    arl
    -0.59
    dit
    -0.59
    chest
    -0.58
    amina
    -0.58
     Subject
    -0.58
    anke
    -0.58
    POSITIVE LOGITS
     unfold
    1.59
     firsthand
    1.41
     happen
    1.32
     emerge
    1.30
     explode
    1.17
     evolve
    1.16
     crumble
    1.14
     soar
    1.14
     occur
    1.13
     unfolding
    1.13
    Activations Density 0.417%

    No Known Activations