INDEX

Explanations

phrases or words indicating strong intensity or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OrNil

-0.82

ſelves

-0.78

 StatefulWidget

-0.78

tagHelperRunner

-0.76

PerformLayout

-0.75

 myſelf

-0.75

 themſelves

-0.73

enderror

-0.73

 AppColors

-0.73

 defaultstate

-0.72

POSITIVE LOGITS

 nearly

0.81

 rounds

0.80

 almost

0.78

 practically

0.73

nearly

0.70

 round

0.69

almost

0.67

 Almost

0.58

databind

0.57

 Douglas

0.56

Activations Density 0.095%

phrases or words indicating strong intensity or emphasis

No Comments

No Known Activations