INDEX

Explanations

mentions of the word "hunter."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fernanda

-0.91

PhysRev

-0.88

 &___

-0.88

 Tivoli

-0.82

 mérit

-0.81

 ressort

-0.81

rrggbb

-0.81

存于互联网档案馆

-0.81

CppMethod

-0.80

 Flamingo

-0.80

POSITIVE LOGITS

 Hunter

1.28

Hunter

1.17

 HUNTER

1.03

 Fenton

0.96

 hunter

0.95

hunter

0.95

 Hunters

0.90

 Newcastle

0.81

 hunters

0.81

 Haller

0.80

Activations Density 0.015%

mentions of the word "hunter."

No Comments

No Known Activations