INDEX

Explanations

terms related to educators and teaching roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Ĩ

-0.87

وذ

-0.82

mopol

-0.76

AsyncResult

-0.75

voerd

-0.73

σιμοποι

-0.71

janos

-0.69

 Sloane

-0.69

 bodyParser

-0.69

AndView

-0.68

POSITIVE LOGITS

 teachers

2.01

 Teachers

1.78

 teacher

1.77

Teachers

1.68

teachers

1.67

 Teacher

1.66

teacher

1.58

 TEACHER

1.52

 TEACHERS

1.46

Teacher

1.44

Activations Density 0.037%

terms related to educators and teaching roles

No Comments

No Known Activations