INDEX

Explanations

terms related to sharpness and precision

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

yled

-0.71

 Fonda

-0.68

RegistryLite

-0.68

ViewImports

-0.67

 Mule

-0.67

seamnă

-0.66

 BrowserModule

-0.66

zeiro

-0.65

RTRS

-0.65

ayout

-0.64

POSITIVE LOGITS

 sharp

2.53

 Sharp

2.37

sharp

2.24

Sharp

2.17

 SHARP

2.12

 sharper

1.89

 sharpness

1.81

 sharpen

1.66

 sharply

1.65

 sharpening

1.50

Activations Density 0.059%

terms related to sharpness and precision

No Comments

No Known Activations