INDEX

Explanations

ellipses or repeated punctuation indicating hesitation or trailing off

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

djangoproject

-0.86

 Glanz

-0.84

 تضيفلها

-0.82

 monoxide

-0.81

databind

-0.81

onnaissance

-0.80

CascadeType

-0.79

riwal

-0.78

bigr

-0.77

POSITIVE LOGITS

.........

1.01

 Jennings

0.83

 .....

0.82

.....

0.80

hibernate

0.79

…..

0.78

 Pohl

0.78

 ....

0.76

drawiam

0.74

!!!!!

0.73

Activations Density 0.148%

ellipses or repeated punctuation indicating hesitation or trailing off

No Comments

No Known Activations