INDEX

Explanations

references to landscapes or outdoor settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-0.99

 ſeveral

-0.98

 itſelf

-0.96

 سكانية

-0.96

 Theſe

-0.94

 uſed

-0.93

 ſtand

-0.92

Personendaten

-0.92

 auffi

-0.91

 pleaſure

-0.89

POSITIVE LOGITS

ju

0.72

 landscape

0.60

av

0.57

 case

0.56

ic

0.55

 cast

0.54

facts

0.54

 facts

0.53

 doing

0.53

 caso

0.52

Activations Density 0.197%

references to landscapes or outdoor settings

No Comments

No Known Activations