INDEX

Explanations

entities categorized by their classifications or groups

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

XtraGrid

-0.86

'',

-0.84

''

-0.83

RLock

-0.81

[],

-0.80

 otomatig

-0.79

ตร์

-0.76

Poems

-0.74

 Penh

-0.73

 puentes

-0.71

POSITIVE LOGITS

 category

1.35

 categories

1.19

 getCategory

1.17

 CATEGORY

1.15

category

1.12

 Category

1.10

Category

1.05

categories

1.02

getCategory

0.98

CATEGORY

0.95

Activations Density 0.149%

entities categorized by their classifications or groups

No Comments

No Known Activations