INDEX

Explanations

phrases indicating the presence of ongoing actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RetentionPolicy

-0.82

bootstrapcdn

-0.79

 Winaray

-0.76

Pfalz

-0.76

 pinulongan

-0.73

 AttributeSet

-0.71

 nakalista

-0.69

 rotates

-0.69

 متعلقه

-0.65

 CLOUD

-0.65

POSITIVE LOGITS

we

1.00

We

0.96

We

0.77

 ourselves

0.73

 Мы

0.71

WE

0.69

 Estamos

0.69

we

0.69

Somos

0.66

 siamo

0.66

Activations Density 0.134%

phrases indicating the presence of ongoing actions or states

No Comments

No Known Activations