INDEX

Explanations

specific names and references related to authors or contributors in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

RetentionPolicy

-0.93

Geplaatst

-0.93

SequentialGroup

-0.85

InputBorder

-0.84

 autorytatywna

-0.84

 للاسماء

-0.83

 Meksiku

-0.81

iffance

-0.81

setVerticalGroup

-0.81

Jeografia

-0.80

POSITIVE LOGITS

Jr

0.75

who

0.55

(@

0.55

Jr

0.52

0.51

PhD

0.51

who

0.48

Sr

0.48

jr

0.48

0.46

Activations Density 0.612%

specific names and references related to authors or contributors in a document

No Comments

No Known Activations