INDEX

Explanations

variations of the word "have" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

]")]

-0.68

:✨

-0.68

setVerticalGroup

-0.63

 ainfi

-0.63

 feroit

-0.63

ſelves

-0.61

itness

-0.60

CompilerServices

-0.60

 themſelves

-0.59

 Portail

-0.59

POSITIVE LOGITS

 been

2.41

 gotten

1.94

been

1.79

 gone

1.76

 taken

1.70

 begun

1.51

 undergone

1.46

 BEEN

1.45

 done

1.39

 Been

1.38

Activations Density 0.629%

variations of the word "have" in different contexts

No Comments

No Known Activations