INDEX

Explanations

instances of the word "often" 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Chartres

-0.69

脚注の使い方

-0.65

 klubben

-0.65

 iParam

-0.64

zura

-0.64

 stringBuilder

-0.63

zedł

-0.63

hydrogenase

-0.63

 Reim

-0.62

 useDispatch

-0.62

POSITIVE LOGITS

 times

1.07

 often

0.98

times

0.95

 Often

0.93

Often

0.90

often

0.89

 Orrell

0.85

 menudo

0.84

 TIMES

0.80

 oftentimes

0.80

Activations Density 0.057%

instances of the word "often" in various contexts

No Comments

No Known Activations