INDEX

Explanations

expressions of gratitude or requests for help

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

LookAnd

-0.85

 Савезне

-0.82

aarrggbb

-0.75

Portail

-0.72

انجليز

-0.70

Personensuche

-0.68

 CreateTagHelper

-0.65

SBATCH

-0.64

ellido

-0.64

 ModelExpression

-0.63

POSITIVE LOGITS

AutoScale

0.49

 beforehand

0.49

 anyone

0.48

WriteLiteral

0.48

0.46

を迎

0.45

Any

0.45

Any

0.45

onOptions

0.44

dnn

0.44

Activations Density 0.101%

expressions of gratitude or requests for help

No Comments

No Known Activations