INDEX

Explanations

repeated mentions of insurance and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Majefty

-1.19

 Chriftian

-1.15

 Diſ

-1.11

 Monfieur

-1.09

Eſ

-1.07

 poffible

-1.06

 itſelf

-1.06

 myſelf

-1.05

 raiſ

-1.04

 Reſ

-1.04

POSITIVE LOGITS

 attention

0.75

 acute

0.65

 insurance

0.61

 Acute

0.60

ate

0.56

 aten

0.55

 Attention

0.54

Acute

0.53

 ATTENTION

0.52

attention

0.52

Activations Density 0.112%

repeated mentions of insurance and related terms

No Comments

No Known Activations