INDEX

Explanations

scientific measurements and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.60

↵↵

-0.55

-0.53

topus

-0.49

 Draht

-0.48

⎢

-0.47

bad

-0.47

The

-0.47

POSITIVE LOGITS

ंदीखरीदारी

0.97

 Савезне

0.95

AnchorStyles

0.91

AddTagHelper

0.89

 kasarigan

0.86

 مشين

0.84

 ExecuteAsync

0.84

interopRequire

0.82

 كومونز

0.81

RectangleBorder

0.77

Activations Density 0.543%

scientific measurements and numerical data

No Comments

No Known Activations