INDEX

Explanations

words that signify transitions or changes in context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Tikang

-0.76

OGND

-0.71

QWidget

-0.66

 BoxFit

-0.65

 ddelweddau

-0.65

 tetrachloride

-0.64

GEBURTSDATUM

-0.64

पया

-0.62

 onCreateView

-0.61

κτηρισ

-0.59

POSITIVE LOGITS

 turns

0.81

CrossRef

0.76

Turns

0.72

 Turns

0.67

 disparu

0.62

 aggiun

0.60

 roles

0.60

artifactId

0.59

 deficit

0.58

 piele

0.58

Activations Density 0.160%

words that signify transitions or changes in context

No Comments

No Known Activations