© 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. 18675
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "In"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "In" followed by numeric values indicating statements or reports

    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
     unemploy
    -0.84
     behav
    -0.62
     (>
    -0.62
     nurt
    -0.60
     artif
    -0.60
    ilogy
    -0.59
    $$
    -0.58
     Dragonbound
    -0.57
     extraord
    -0.57
     yourselves
    -0.57
    POSITIVE LOGITS
    spect
    1.32
    cluded
    1.26
    cluding
    1.22
    ventory
    1.14
     addition
    1.13
    jured
    1.04
    clude
    1.04
    iti
    1.03
    aug
    1.03
    mates
    0.99
    Activations Density 0.102%

    No Known Activations