INDEX

Explanations

instances of quantitative data or numerical references

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

Citations or references

np_acts-logits-general · gemini-2.0-flash

academic papers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

+#+#

-0.76

 tartalomajánló

-0.74

Jereo

-0.74

 mergeFrom

-0.72

 Italijanski

-0.71

Izvori

-0.69

Халык

-0.69

ⓧ

-0.68

 exemplaires

-0.67

 ब्रेकडाउन

-0.66

POSITIVE LOGITS

<bos>

0.47

тала

0.46

Personendaten

0.45

ouf

0.44

<tbody>

0.42

umma

0.41

chuck

0.41

 tập

0.40

 pras

0.40

agaan

0.40

Activations Density 0.182%

instances of quantitative data or numerical references

Citations or references

academic papers

No Comments

No Known Activations