INDEX

Explanations

references to serious issues or problems

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

MigrationBuilder

-0.94

 "..\..\..\

-0.92

LookAnd

-0.73

 "..\..\

-0.73

 détru

-0.68

swt

-0.67

 détruit

-0.67

ربای

-0.66

 JpaRepository

-0.66

 stoichio

-0.66

POSITIVE LOGITS

 serious

2.82

 Serious

2.64

Serious

2.58

serious

2.57

 seriously

2.00

 seriousness

1.97

 sérieux

1.94

 serius

1.83

 serio

1.83

 sério

1.74

Activations Density 0.076%

references to serious issues or problems

No Comments

No Known Activations