INDEX

Explanations

verbs or actions associated with specific tasks or roles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.61

vs

-0.60

to

-0.56

vr

-0.53

-0.52

-0.50

nbsp

-0.49

↵

-0.49

er

-0.48

POSITIVE LOGITS

 CreateTagHelper

1.17

Autoritní

1.09

 estimés

1.01

ContentAsync

0.95

tagHelperRunner

0.93

DoubleQuotes

0.89

 varandra

0.88

 Normdatei

0.87

Referències

0.87

0.85

Activations Density 0.212%

verbs or actions associated with specific tasks or roles

No Comments

No Known Activations