INDEX

Explanations

entities related to specific names, places, and terminology in historical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 Isaacs

-0.76

Bran

-0.73

 pró

-0.71

 Rivers

-0.70

Rivers

-0.65

TagNumber

-0.64

Hé

-0.64

icel

-0.63

prins

-0.63

')))

-0.61

POSITIVE LOGITS

 myſelf

0.98

 itſelf

0.89

 doubtnut

0.83

 Lomb

0.83

ตร์

0.82

 Shakspeare

0.81

 drôle

0.79

ύ

0.79

Kew

0.78

 themſelves

0.77

Activations Density 2.571%

entities related to specific names, places, and terminology in historical or scientific contexts

No Comments

No Known Activations