© 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. 7-RES-JB
    11. 17135
    Prev
    Next
    INDEX
    Explanations

    references related to the term "Ninety"

    oai_token-act-pair · gpt-3.5-turbo

    references to the number ninety or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.73
     ASC
    -0.71
     Hilton
    -0.63
     mileage
    -0.62
     Miranda
    -0.60
     shake
    -0.60
     bearer
    -0.59
     placement
    -0.58
     carriers
    -0.58
     fault
    -0.58
    POSITIVE LOGITS
    eteen
    1.91
    eteenth
    1.79
    eties
    1.48
    ety
    1.46
    jas
    1.32
    ovember
    1.12
    jah
    1.09
    ormal
    1.08
    ja
    1.06
    umbered
    1.01
    Activations Density 0.027%

    No Known Activations