INDEX

Explanations

references to notable achievements and recognition

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

Tokens preceding "References" or "Category"

np_acts-logits-general · gemini-2.0-flash

References and categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 därför

-0.52

 pitä

-0.49

 handelt

-0.45

 eccell

-0.44

 stiamo

-0.44

 abstrait

-0.43

 both

-0.42

 sowohl

-0.42

POSITIVE LOGITS

脚注の使い方

1.03

 References

1.02

contentLoaded

0.99

 ujednoznacz

0.93

 references

0.93

 bezeichneter

0.91

 Notes

0.90

References

0.89

ⓘ

0.89

 مشين

0.89

Activations Density 0.386%

references to notable achievements and recognition

Tokens preceding "References" or "Category"

References and categories

No Comments

No Known Activations