INDEX

Explanations

references to the concept of returning or coming back in various contexts

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

"back" followed by "then" or "in"

np_acts-logits-general · gemini-2.0-flash

back then, back in

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Efq

-0.84

 itſelf

-0.84

setVerticalGroup

-0.83

 whoſe

-0.83

 myſelf

-0.80

 chofe

-0.79

resave

-0.78

 themſelves

-0.77

 ſtate

-0.77

WaitGroup

-0.76

POSITIVE LOGITS

 back

0.81

 Back

0.75

Back

0.71

back

0.70

 BACK

0.62

0.60

gam

0.53

on

0.53

BACK

0.52

 Référence

0.51

Activations Density 0.043%

references to the concept of returning or coming back in various contexts

"back" followed by "then" or "in"

back then, back in

No Comments

No Known Activations