INDEX

Explanations

references to modifications, updates, and improvements made to processes or systems

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

alterations or adjustments

np_acts-logits-general · gemini-2.0-flash

changes, improvements, modifications

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

########.

-0.49

 svolge

-0.47

 розви

-0.46

kå

-0.46

ervlak

-0.46

 renewed

-0.44

àm

-0.44

othelial

-0.44

URIS

-0.43

ότητα

-0.43

POSITIVE LOGITS

 apport

0.92

 apporté

0.79

 changes

0.79

 Changes

0.74

 changements

0.73

 vorgenommen

0.71

 affecting

0.71

Changes

0.70

 effected

0.68

 necessitated

0.67

Activations Density 0.525%

references to modifications, updates, and improvements made to processes or systems

alterations or adjustments

changes, improvements, modifications

No Comments

No Known Activations