INDEX

Explanations

documents that focus on summary evaluations or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ་་

-1.34

^(@)

-1.34

 purpoſe

-1.34

Efq

-1.32

 Anſ

-1.29

 ―――――

-1.28

ſelves

-1.27

expandindo

-1.27

 Forumite

-1.25

ſelf

-1.25

POSITIVE LOGITS

0.83

0.81

//

0.79

and

0.78

0.77

0.76

 summary

0.75

↵

0.73

Activations Density 0.185%

documents that focus on summary evaluations or conclusions

No Comments

No Known Activations