INDEX

Explanations

phrases related to permissions and legal frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 equipments

-0.82

 Nowadays

-0.72

 habitants

-0.64

<eos>

-0.63

慢慢的

-0.63

-0.62

 nowadays

-0.61

Nowadays

-0.60

 advices

-0.59

POSITIVE LOGITS

FWIW

0.96

].)

0.94

eabouts

0.93

YMMV

0.91

 ་་

0.90

berdayakan

0.90

sedown

0.89

وأضاف

0.88

issipp

0.87

\<^

0.87

Activations Density 6.718%

phrases related to permissions and legal frameworks

No Comments

No Known Activations