INDEX

Explanations

words related to software or programming concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Pre

-0.49

Su

-0.46

Su

-0.46

abs

-0.45

р

-0.45

↵

-0.45

pre

-0.45

庄

-0.45

POSITIVE LOGITS

 Савезне

1.07

)");

0.95

expandindo

0.93

 Réponses

0.93

TagMode

0.92

BeginContext

0.89

CloseOperation

0.89

ViewFeatures

0.88

 الاطلاع

0.87

 snippetHide

0.85

Activations Density 0.041%

words related to software or programming concepts and terms

No Comments

No Known Activations