INDEX

Explanations

various forms of punctuation and their usage in written language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

the

-0.56

-0.50

 both

-0.50

both

-0.46

 audits

-0.45

Both

-0.43

 chapters

-0.42

its

-0.42

 fragments

-0.42

 forecasts

-0.41

POSITIVE LOGITS

yet

0.91

 albeit

0.84

yet

0.81

 often

0.79

 sometimes

0.73

 oftentimes

0.73

often

0.69

 للمعارف

0.69

albeit

0.68

oft

0.65

Activations Density 0.256%

various forms of punctuation and their usage in written language

No Comments

No Known Activations