INDEX

Explanations

instances of the word "walk" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 suprême

-0.93

 Darmstadt

-0.89

 navideños

-0.87

 Brenner

-0.86

 miatt

-0.82

 cielos

-0.81

kirakan

-0.78

 licorne

-0.78

 héri

-0.77

 religiosos

-0.76

POSITIVE LOGITS

 walk

2.22

 WALK

2.11

 Walk

2.09

walk

2.09

 walks

2.03

Walk

2.03

 walking

1.98

 walked

1.94

 Walks

1.89

 Walking

1.87

Activations Density 0.034%

instances of the word "walk" in various forms and contexts

No Comments

No Known Activations