INDEX

Explanations

proper nouns, particularly names of individuals and places

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

+#+#

-0.85

 مشين

-0.75

RectangleBorder

-0.74

تقاوى

-0.73

AnchorStyles

-0.73

 iſt

-0.69

 initWithFrame

-0.68

NewUrlParser

-0.68

 Audiodateien

-0.66

 المعيارى

-0.65

POSITIVE LOGITS

最快更新

0.58

观的

0.55

Har

0.55

来看看

0.54

っこう

0.53

писание

0.52

やら

0.52

nil

0.51

St

0.51

 Shri

0.51

Activations Density 0.525%

proper nouns, particularly names of individuals and places

No Comments

No Known Activations