INDEX

Explanations

expressions of curiosity or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Datuak

-0.85

/***/

-0.66

 createStore

-0.65

 Astoria

-0.63

IRQn

-0.62

-0.61

 Alec

-0.60

 Industri

-0.59

aroa

-0.59

brainly

-0.59

POSITIVE LOGITS

 wonder

1.82

 Wonder

1.81

 wondering

1.76

wonder

1.74

Wonder

1.72

 WONDER

1.62

 wondered

1.55

 wonders

1.44

Wondering

1.44

 Wonders

1.35

Activations Density 0.050%

expressions of curiosity or questioning

No Comments

No Known Activations