INDEX

Explanations

the names of specific entities and references to code or technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ddelweddau

-0.64

ніципа

-0.62

 חיצוניים

-0.61

NUMX

-0.59

 saurait

-0.56

”？

-0.53

дә

-0.53

?',

-0.52

ineno

-0.52

ATURE

-0.52

POSITIVE LOGITS

ull

0.62

initComponents

0.56

onViewCreated

0.55

DJANGO

0.55

AsUp

0.54

ick

0.54

 psycopg

0.54

ById

0.53

/></

0.53

❃

0.52

Activations Density 2.496%

the names of specific entities and references to code or technical terms

No Comments

No Known Activations