INDEX

Explanations

verbs related to expressing opinions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

GenerationType

-0.73

interopRequire

-0.63

yntaxException

-0.61

tagHelperRunner

-0.60

TintMode

-0.58

AccessFile

-0.57

FormTagHelper

-0.57

Karakteristik

-0.55

AutoScale

-0.55

 installment

-0.54

POSITIVE LOGITS

 expressing

1.33

 expressed

1.30

 express

1.23

 expresses

1.23

expressed

1.08

 EXPRESS

1.07

Express

1.07

 uttry

1.05

expressing

1.03

express

1.01

Activations Density 0.583%

verbs related to expressing opinions or statements

No Comments

No Known Activations