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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18372
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives that indicate a degree or level of intensity

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating frequency or degree of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -0.95
    ODY
    -0.81
     Tags
    -0.79
     Guys
    -0.78
    ydia
    -0.76
     Dreams
    -0.74
    ĺħ
    -0.71
    terday
    -0.69
     Females
    -0.69
     Releases
    -0.68
    POSITIVE LOGITS
     chaotic
    1.06
     tumultuous
    1.03
     turbulent
    1.00
     convoluted
    0.98
     embattled
    0.98
     controversial
    0.97
     volatile
    0.96
     contradictory
    0.96
     contentious
    0.95
     lucrative
    0.94
    Activations Density 0.184%

    No Known Activations