INDEX

Explanations

phrases indicating alternative conditions or contrasting scenarios

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

 Jagger

-0.68

ânsito

-0.67

HideFlags

-0.66

 spoloč

-0.64

 Checkpoint

-0.61

gido

-0.61

uasaan

-0.61

shafen

-0.60

 endwhile

-0.60

 aantal

-0.60

POSITIVE LOGITS

 Otherwise

1.06

Otherwise

1.02

 OTHERWISE

0.95

 otherwise

0.94

otherwise

0.85

 Else

0.80

wise

0.79

BackStack

0.76

Else

0.76

 acost

0.73

Activations Density 0.067%

phrases indicating alternative conditions or contrasting scenarios

No Comments

No Known Activations