INDEX

Explanations

references to accessibility and inclusion in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

OrBuilder

-0.59

setof

-0.51

uegos

-0.49

ctu

-0.49

fahrene

-0.48

billon

-0.46

ROUT

-0.44

Externe

-0.44

iNdEx

-0.43

༽

-0.43

POSITIVE LOGITS

 accessibility

1.01

 accessible

0.96

 access

0.93

 acces

0.88

 affordability

0.86

 accesible

0.85

 democrati

0.83

 ACCESS

0.82

 affordable

0.82

 Accessibility

0.82

Activations Density 0.221%

references to accessibility and inclusion in various contexts

No Comments

No Known Activations