INDEX

Explanations

quantitative data and numerical values

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.63

″

-0.57

-0.56

-0.55

-0.53

nd

-0.52

-0.51

POSITIVE LOGITS

tieth

0.84

 hundred

0.83

fold

0.75

 thousand

0.72

hundred

0.69

fifths

0.68

teenth

0.67

cientos

0.66

teen

0.65

teens

0.65

Activations Density 0.451%

quantitative data and numerical values

No Comments

No Known Activations