INDEX

Explanations

words associated with specific brands, companies, or medical terminology

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

modelBuilder

-0.86

MigrationBuilder

-0.73

addPreferredGap

-0.68

 NSCoder

-0.67

/***/

-0.67

malink

-0.66

">//

-0.65

DockStyle

-0.64

__*/

-0.62

 lenker

-0.61

POSITIVE LOGITS

hes

0.56

key

0.55

kej

0.54

hed

0.50

lub

0.50

ci

0.50

keys

0.49

ke

0.49

irc

0.48

JoinColumn

0.48

Activations Density 0.286%

words associated with specific brands, companies, or medical terminology

No Comments

No Known Activations