INDEX

Explanations

phrases indicating conditions or classifications regarding employment practices

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

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

 Teacher

-0.74

 teacher

-0.73

Teacher

-0.72

 Teachers

-0.72

terminal

-0.70

Treasurer

-0.70

teacher

-0.68

TextView

-0.68

 Texas

-0.68

 token

-0.67

POSITIVE LOGITS

brainly

0.57

Rüyada

0.53

Autoritní

0.53

UVWXYZ

0.50

исленность

0.50

Hauptartikel

0.49

culous

0.49

ellees

0.48

DockStyle

0.47

andowski

0.47

Activations Density 0.373%

phrases indicating conditions or classifications regarding employment practices

No Comments

No Known Activations