INDEX

Explanations

phrases and words related to identity and social status

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

Japanese text followed by particles

np_acts-logits-general · gemini-2.0-flash

emotions and states of being

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

Normally

-0.46

 Normally

-0.45

cesz

-0.43

-0.42

 birlikte

-0.41

以外は

-0.40

 şekilde

-0.40

 normalt

-0.39

 empleo

-0.39

으로

-0.39

POSITIVE LOGITS

 مشين

0.91

 MainAxisSize

0.82

AxisAlignment

0.77

frastructure

0.74

oredCriteria

0.74

 BorderRadius

0.74

'],

0.73

enumi

0.72

 MessageBoxIcon

0.71

jsxFileName

0.69

Activations Density 0.098%

phrases and words related to identity and social status

Japanese text followed by particles

emotions and states of being

No Comments

No Known Activations