INDEX

Explanations

the word "in" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 سكانية

-0.86

 Forumite

-0.84

 مشين

-0.83

 GenerationType

-0.83

utilisons

-0.82

OGND

-0.77

NameInMap

-0.77

 propOrder

-0.76

évaluateur

-0.74

 protoimpl

-0.74

POSITIVE LOGITS

 acetic

0.74

ing

0.69

 Pfeiffer

0.63

foria

0.60

Nina

0.60

hagic

0.58

 συ

0.58

τύ

0.58

द्र

0.58

Animator

0.58

Activations Density 0.045%

the word "in" in various contexts

No Comments

No Known Activations