INDEX

Explanations

phrase related to product features and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 skla

-0.42

 tarifa

-0.41

[][]

-0.41

 group

-0.41

여

-0.41

 radiate

-0.41

 mass

-0.41

 blankets

-0.41

loven

-0.41

 leggi

-0.40

POSITIVE LOGITS

 collar

0.88

DebuggerNonUser

0.85

 onOptions

0.77

migrationBuilder

0.77

 متعلقه

0.76

 Roskov

0.75

 Collar

0.74

collar

0.74

 cuffs

0.74

 الحره

0.73

Activations Density 0.070%

phrase related to product features and descriptions

No Comments

No Known Activations