INDEX

Explanations

references to specific locations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Alaska

-0.80

Alaska

-0.78

 Alaskan

-0.78

 transfieras

-0.73

 Valdez

-0.72

 BoxFit

-0.70

 nahilalakip

-0.68

 alaska

-0.65

 RCMP

-0.64



-0.59

POSITIVE LOGITS

 nakalista

0.92

MPP

0.66

 Athenian

0.62

 Mississauga

0.62

 Paulista

0.61

 Yoruba

0.59

 فريبيس

0.59

 Ptole

0.58

 Duomo

0.57

 Toronto

0.55

Activations Density 0.083%

references to specific locations or institutions

No Comments

No Known Activations