INDEX

Explanations

references to "boy" and "joy" in various contexts

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

itated

-0.65

 fresca

-0.63

///</

-0.63

Blurb

-0.61

afu

-0.60

adalupe

-0.60

weet

-0.60

 WebApplication

-0.60

BindingResult

-0.60

-0.59

POSITIVE LOGITS

Doy

0.70

Koy

0.62

ROY

0.59

Joy

0.57

toy

0.56

oy

0.55

JOY

0.55

Roy

0.54

Goy

0.53

JOY

0.53

Activations Density 0.082%

references to "boy" and "joy" in various contexts

No Comments

No Known Activations