© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10100
    Prev
    Next
    INDEX
    Explanations

    instances of the word "present" or related forms

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "present" in various contexts

    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
    STAR
    -0.75
    weed
    -0.67
    imov
    -0.67
    isexual
    -0.67
    terness
    -0.66
    jar
    -0.66
    kick
    -0.63
     Runs
    -0.62
    lez
    -0.61
     BET
    -0.61
    POSITIVE LOGITS
    iment
    1.38
    iments
    1.22
     tense
    1.09
    ational
    1.02
    imental
    1.02
    encing
    0.96
    eering
    0.93
    able
    0.92
     invention
    0.89
    ative
    0.86
    Activations Density 0.042%

    No Known Activations