INDEX

Explanations

references to relationships between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

šanās

-0.52

Hod

-0.50

Sey

-0.47

pcl

-0.47

 yanı

-0.47

bsd

-0.47

Portály

-0.46

 îna

-0.46

idelberg

-0.46

Elijah

-0.46

POSITIVE LOGITS

IntoConstraints

0.88

WriteTagHelper

0.85

ftagPool

0.74

 kasarigan

0.73

writerow

0.71

impinan

0.69

AndEndTag

0.69

หวัด

0.69

WriteBarrier

0.68

########.

0.67

Activations Density 0.830%

references to relationships between entities

No Comments

No Known Activations