INDEX

Explanations

references to significant historical events and entities

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

 }^{[

-0.66

ionine

-0.50

šk

-0.49

 skri

-0.47

Intra

-0.46

setNome

-0.46

bingen

-0.46

IVITY

-0.45

Mess

-0.45

psz

-0.45

POSITIVE LOGITS

 Qaeda

1.02

 terrorism

0.98

 Terrorism

0.87

 terrorist

0.86

 terrorists

0.84

Qaeda

0.84

terror

0.80

 Osama

0.80

Terror

0.77

Попис

0.75

Activations Density 0.268%

references to significant historical events and entities

No Comments

No Known Activations