INDEX

Explanations

terms related to biological structures, functions, and interactions

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

following action verbs

np_acts-logits-general · gemini-2.0-flash

from a noun

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

setViewportView

-0.50

 autorytatywna

-0.49

請繼續往下閱讀

-0.49

 Tatum

-0.49

 Theſe

-0.48

genheit

-0.47

FieldDescriptor

-0.47

ợp

-0.46

 HelloWorld

-0.45

 विश्वसनीयता

-0.45

POSITIVE LOGITS

ArgsConstructor

0.81

basicConfig

0.74

TintMode

0.72

SBATCH

0.69

ритори

0.69

 ويكيميديا

0.67

XmlAccessorType

0.66

TagMode

0.65

 Audiodateien

0.64

Посилання

0.64

Activations Density 3.407%

terms related to biological structures, functions, and interactions

following action verbs

from a noun

No Comments

No Known Activations