INDEX

Explanations

references to users and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 يتيمه

-1.05

脚注の使い方

-0.89

ArgsConstructor

-0.89

AndEndTag

-0.88

OGND

-0.88

 utafitiHapana

-0.88

 itſelf

-0.87

]-->

-0.85

 myſelf

-0.85

 समीक्षाओं

-0.85

POSITIVE LOGITS

0.51

gli

0.49

 <<<<<<<<<<<<<<

0.47

 vaste

0.46

le

0.45

Всем

0.44

 столько

0.44

ScopeManager

0.43

 те

0.42

an

0.42

Activations Density 0.469%

references to users and their interactions

No Comments

No Known Activations