INDEX

Explanations

phrases that emphasize quantities or measures in a context

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

 समीक्षक

-0.61

ன்று

-0.53

uxxxx

-0.50

ışı

-0.50

 afla

-0.48

-0.46

 frei

-0.46

nextDouble

-0.44

 parall

-0.44

ছে

-0.44

POSITIVE LOGITS

RUnlock

0.79

writeFieldEnd

0.75

RegistryLite

0.73

qxd

0.72

 ویکی‌پدی

0.72

galus

0.71

FormTagHelper

0.71

RegressionTest

0.70

UnknownFieldSet

0.68

 ostavi

0.68

Activations Density 0.131%

phrases that emphasize quantities or measures in a context

No Comments

No Known Activations