INDEX

Explanations

sequences that indicate the relationship between subjects and their actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 gepubliceerd

-0.55

 Majefty

-0.52

 vang

-0.52

 Rhine

-0.50

OWSKI

-0.50

revalidate

-0.50

 Diſ

-0.49

 Perſ

-0.48

iconque

-0.48

しかも

-0.48

POSITIVE LOGITS

fromnode

0.78

mybatisplus

0.73

########.

0.72

SourceChecksum

0.70

ReusableCell

0.68

AndroidJUnit

0.66

Хьажоргаш

0.66

хьтан

0.66

 Pristupljeno

0.66

Enllaces

0.65

Activations Density 0.699%

sequences that indicate the relationship between subjects and their actions or states

No Comments

No Known Activations