INDEX

Explanations

references to mountains and mountainous landscapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 DELHI

-0.73

djangoproject

-0.68

çais

-0.66

ukkah

-0.65

lankton

-0.63

 Jacksonville

-0.61

datastore

-0.59

asString

-0.58

 CHICAGO

-0.58

ARGB

-0.57

POSITIVE LOGITS

 mountain

1.60

 hills

1.58

 Mountain

1.57

 mountains

1.52

 hill

1.48

Mountain

1.44

 Mountains

1.40

 Mount

1.39

mountain

1.36

 MOUNTAIN

1.33

Activations Density 0.166%

references to mountains and mountainous landscapes

No Comments

No Known Activations