INDEX

Explanations

references to specific locations, particularly schools and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 виправивши

-0.59

 насељу

-0.55

 Luci

-0.55

GMENT

-0.53

 diş

-0.49

XmlAccessType

-0.49

 chandelier

-0.47

 ansehen

-0.46

 Pang

-0.46

 Albright

-0.46

POSITIVE LOGITS

 Brooklyn

1.01

Brooklyn

0.89

 Queens

0.82

 brooklyn

0.82

Queens

0.73

 Staten

0.68

 BROOK

0.64

 فريبيس

0.62

 للاسماء

0.60

 queens

0.59

Activations Density 0.127%

references to specific locations, particularly schools and communities

No Comments

No Known Activations