INDEX

Explanations

repetitive phrases indicating recurrence or emphasis in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

kano

-0.91

 Hernando

-0.70

 Hale

-0.70

€¢

-0.69

vfs

-0.67

 Swain

-0.64

\_\_

-0.64

 Bryant

-0.64

 Bavarian

-0.63

pertino

-0.63

POSITIVE LOGITS

TestingModule

0.92

AGAIN

0.87

 AGAIN

0.86

 again

0.84

 Again

0.82

 Audiodateien

0.82

jsdelivr

0.81

Again

0.81

again

0.80

AsUp

0.74

Activations Density 0.037%

repetitive phrases indicating recurrence or emphasis in a narrative

No Comments

No Known Activations