INDEX

Explanations

instances of the word "had" as a significant term in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Olsson

-0.96

 Reuter

-0.83

 Torrey

-0.82

LLocation

-0.81

 Guen

-0.81

 Dickinson

-0.80

SLS

-0.80

 Hutchins

-0.80

Rek

-0.79

 Bask

-0.78

POSITIVE LOGITS

Had

1.59

had

1.54

Had

1.51

HAD

1.49

had

1.32

HAD

1.07

 hadn

0.96

 hatten

0.96

 avaient

0.94

 hatte

0.94

Activations Density 0.104%

instances of the word "had" as a significant term in the text

No Comments

No Known Activations