INDEX

Explanations

phrases related to expertise and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RectangleBorder

-0.70

-0.64

 Worse

-0.55

 alibi

-0.55

ⓘ

-0.55

ftagPool

-0.53

 bienven

-0.53

 supposed

-0.53

دیگر

-0.53

 noce

-0.51

POSITIVE LOGITS

 offices

0.67

 extensive

0.65

offices

0.57

 numerous

0.57

 širo

0.54

ReusableCell

0.53

Билгалдахарш

0.53

 many

0.52

 vast

0.52

extensive

0.52

Activations Density 0.142%

phrases related to expertise and experience

No Comments

No Known Activations