INDEX

Explanations

references to organizations or entities related to health and treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ILayout

-0.56

sho

-0.56

 item

-0.50

 inode

-0.49

 institution

-0.48

 acting

-0.46

GLFW

-0.46

apo

-0.46

lint

-0.45

exclu

-0.44

POSITIVE LOGITS

ros

1.01

 متعلقه

0.82

Ros

0.76

 sumpay

0.75

rungsseite

0.72

 Radio

0.69

Ros

0.69

Radio

0.67

__':

0.67

</tfoot>

0.65

Activations Density 0.148%

references to organizations or entities related to health and treatment

No Comments

No Known Activations