INDEX

Explanations

terms related to the generation or production of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SPATH

-0.79

 nicio

-0.70

 griega

-0.67

 scorso

-0.64

 owls

-0.63

 sockaddr

-0.61

 pitié

-0.61

 grecque

-0.60

 intValue

-0.60

 Chernobyl

-0.60

POSITIVE LOGITS

 Generates

1.42

GENER

1.35

 generators

1.33

 Generated

1.32

 Generation

1.30

 generator

1.27

 generation

1.26

 GENER

1.26

 Generator

1.25

 Generators

1.20

Activations Density 0.115%

terms related to the generation or production of something

No Comments

No Known Activations