INDEX

Explanations

references to various roles and positions in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

marle

-0.60

PerformLayout

-0.56

 المعيارى

-0.52

Portale

-0.50

sizeCache

-0.50

clientHeight

-0.50

tonsoft

-0.50

oredCriteria

-0.49

ApiModel

-0.48

vå

-0.48

POSITIVE LOGITS

 tasks

1.59

 duties

1.47

 roles

1.42

 Tasks

1.38

 Duties

1.28

tasks

1.28

 jobs

1.25

 respon

1.24

 Roles

1.19

 chores

1.16

Activations Density 0.127%

references to various roles and positions in different contexts

No Comments

No Known Activations