INDEX

Explanations

the presence of the word "Cap" and its variations in different contexts

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

}?>

-0.61

igate

-0.60

 fiche

-0.60

anyahu

-0.60

ISTICS

-0.58

ตร์

-0.57

versario

-0.56

enderror

-0.55

Semitism

-0.55

consulté

-0.55

POSITIVE LOGITS

Cap

0.78

Captor

0.76

Cap

0.75

CAP

0.74

Tē

0.74

 caps

0.69

 Caps

0.68

cap

0.66

CAP

0.65

SharedDtor

0.64

Activations Density 0.079%

the presence of the word "Cap" and its variations in different contexts

No Comments

No Known Activations