INDEX

Explanations

terms related to loss or the concept of losing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

complexContent

-1.12

OGND

-1.01

 referenties

-0.94

theless

-0.94

Portail

-0.93

Datuak

-0.87

 resourceCulture

-0.85

ypep

-0.84

حوالہ

-0.82

 complémentaires

-0.82

POSITIVE LOGITS

 loss

2.15

 Loss

2.01

loss

1.91

 LOSS

1.88

Loss

1.87

 losses

1.75

LOSS

1.66

 Losses

1.50

losses

1.44

Losses

1.41

Activations Density 0.052%

terms related to loss or the concept of losing something

No Comments

No Known Activations