INDEX

Explanations

proper nouns and names of companies or legal entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

)");

-0.71

 propOrder

-0.71

)"),

-0.70

](#

-0.67

ReusableCell

-0.66

Personendaten

-0.66

 OMITBAD

-0.66

RenderAtEndOf

-0.65

parsedMessage

-0.65

awtextra

-0.63

POSITIVE LOGITS

Inc

2.59

LLC

2.00

Inc

1.87

INC

1.71

inc

1.60

inc

1.50

 Incorporated

1.43

Ltd

1.37

INC

1.29

llc

1.28

Activations Density 0.353%

proper nouns and names of companies or legal entities

No Comments

No Known Activations