INDEX

Explanations

references to safety and related concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

']?>

-0.76

 McGee

-0.76

 Toussaint

-0.74

Cus

-0.73

canActivate

-0.71

 Tribe

-0.69

zuk

-0.68

weep

-0.67

itecture

-0.67

 isInitialized

-0.65

POSITIVE LOGITS

RequestMapping

0.97

 Plates

0.87

Plates

0.86

LTS

0.85

UserScript

0.84

 Motions

0.81

 plates

0.81

aster

0.80

 Gaston

0.80

 Yarm

0.78

Activations Density 0.087%

references to safety and related concepts in various contexts

No Comments

No Known Activations