INDEX

Explanations

references to photographs and imaging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 photo

-2.88

 Photo

-2.55

Photo

-2.47

photo

-2.45

 PHOTO

-1.95

 foto

-1.82

PHOTO

-1.74

 photos

-1.70

 фото

-1.60

 Foto

-1.59

POSITIVE LOGITS

 Penrose

0.57

rode

0.56

жава

0.54

kenny

0.53

zeg

0.53

idue

0.52

entif

0.52

 molten

0.51

ensacola

0.50

 romain

0.50

Activations Density 0.109%

references to photographs and imaging

No Comments

No Known Activations