INDEX

Explanations

instances of the word "determine" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

“

-0.83

-0.81

<strong>

-0.74

-0.66

‘

-0.65

’

-0.64

Millisecond

-0.63

 alto

-0.62

Ha

-0.62

 multi

-0.61

POSITIVE LOGITS

 Determine

2.06

Determine

2.05

 Determines

2.03

 determination

2.01

 determines

1.96

 determine

1.95

 DETERMIN

1.94

 Determining

1.92

determine

1.92

 determined

1.92

Activations Density 0.125%

instances of the word "determine" and its variations

No Comments

No Known Activations