INDEX

Explanations

references to time, specifically the word "last" and variations related to it

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

ConstraintMaker

-0.90

AsUp

-0.86

AndEndTag

-0.78

HasAnnotation

-0.74

 isInitialized

-0.73

 незавершена

-0.72

 صوتيه

-0.71

 referenties

-0.69

GraphicsUnit

-0.69

 ostavi

-0.69

POSITIVE LOGITS

 year

0.89

 week

0.74

 November

0.72

 fall

0.70

 weekend

0.69

 October

0.69

 Friday

0.68

 August

0.65

 month

0.65

 December

0.65

Activations Density 0.050%

references to time, specifically the word "last" and variations related to it

No Comments

No Known Activations