INDEX

Explanations

information related to television programs and their broadcasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 تضيفلها

-0.70

RectangleBorder

-0.67

 écoulé

-0.66

SourceChecksum

-0.65

 RSSSF

-0.65

mmate

-0.64

sqcup

-0.63

 >=",

-0.62

 Профиль

-0.61

पया

-0.60

POSITIVE LOGITS

 television

0.90

 broadcast

0.86

TV

0.82

 broadcasts

0.80

 broadcasting

0.77

 broadcasters

0.77

 Television

0.75

 televis

0.70

 televised

0.66

television

0.66

Activations Density 0.205%

information related to television programs and their broadcasts

No Comments

No Known Activations