INDEX

Explanations

references to downward trends or reductions in any context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 betweenstory

-0.85

 Савезне

-0.78

 nahilalakip

-0.77

Eksterne

-0.76

djangoproject

-0.75

دانشنامهٔ

-0.75

Viki

-0.74

 AssemblyCompany

-0.73

ształ

-0.72

addCriterion

-0.72

POSITIVE LOGITS

 Down

0.96

Down

0.94

 down

0.94

 DOWN

0.90

pour

0.81

down

0.78

DOWN

0.78

downs

0.77

Downs

0.74

sizing

0.73

Activations Density 0.083%

references to downward trends or reductions in any context

No Comments

No Known Activations