INDEX

Explanations

words associated with legal or organizational contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-0.68

 enfans

-0.67

 culturelles

-0.64

didReceive

-0.63

 fermés

-0.63

PreferredItem

-0.63

AndEndTag

-0.63

 mergeFrom

-0.63

 emplois

-0.62

 firent

-0.60

POSITIVE LOGITS

ối

0.52

 configurable

0.52

<bos>

0.48

 asset

0.47

Література

0.47

gex

0.47

बंध

0.46

aaS

0.46

 noqa

0.46

 defen

0.45

Activations Density 0.608%

words associated with legal or organizational contexts

No Comments

No Known Activations