INDEX

Explanations

words and phrases related to actions, perception, and community involvement

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

Preceding adjectives or articles

np_acts-logits-general · gemini-2.0-flash

evaluative adjectives following 'a'

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

MigrationBuilder

-1.03

 ſche

-0.83

 الحره

-0.78

tagHelperRunner

-0.75

 Majefty

-0.71

bootstrapcdn

-0.71

 CreateTagHelper

-0.70

 greateſt

-0.69

 متعلقه

-0.68

IUrlHelper

-0.68

POSITIVE LOGITS

 highly

0.87

 robust

0.77

 effective

0.76

 attractive

0.75

 powerful

0.74

 reliable

0.74

 well

0.74

 safe

0.73

 healthy

0.72

 efficient

0.72

Activations Density 0.705%

words and phrases related to actions, perception, and community involvement

Preceding adjectives or articles

evaluative adjectives following 'a'

No Comments

No Known Activations