INDEX

Explanations

references to types and features of tiles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ंदीखरीदारी

-1.10

Personensuche

-0.90

/*

-0.90

coroutines

-0.84

مصادر

-0.82

ECL

-0.79

StructEnd

-0.79

orghini

-0.79

 StringVar

-0.78

DispatchToProps

-0.78

POSITIVE LOGITS

 tiles

2.10

 tile

2.05

 Tile

1.94

Tile

1.82

 Tiles

1.80

tile

1.75

Tiles

1.72

TILE

1.59

tiles

1.58

 TILE

1.52

Activations Density 0.087%

references to types and features of tiles

No Comments

No Known Activations