INDEX

Explanations

structured data elements and specific formatting symbols

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

 mahal

-0.49

PageContext

-0.48

 government

-0.45

industan

-0.44

 Rég

-0.43

イクアウト

-0.42

 Government

-0.42

 candlestick

-0.41

עת

-0.41

AAAAAAAAAAAAAAAA

-0.41

POSITIVE LOGITS

LookAnd

0.85

aarrggbb

0.84

 pinulongan

0.76

 <=",

0.76

UrlResolution

0.74

 Roskov

0.73

tagHelperRunner

0.73

المشاركات

0.73

TagMode

0.71

 esternos

0.71

Activations Density 0.959%

structured data elements and specific formatting symbols

No Comments

No Known Activations