INDEX

Explanations

instances of the letter 't' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

nõ

-0.55

مؤ

-0.54

ільки

-0.53

ุณ

-0.53

grou

-0.52

 ostavi

-0.52

 Coyle

-0.51

ſy

-0.51

 skjø

-0.51

kwal

-0.50

POSITIVE LOGITS

onedDateTime

1.06

ⓘ

0.92

EndContext

0.90

DoubleQuotes

0.85

multer

0.84

########.

0.81

webElementGuid

0.78

 IndexPath

0.78

extAlignment

0.77

qrstuvwxyz

0.76

Activations Density 0.038%

instances of the letter 't' in various contexts

No Comments

No Known Activations