INDEX

Explanations

programming or technical terminology related to class and method structure

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

AndroidJUnit

-0.54

 Motive

-0.53

 Pressure

-0.52

ConstraintMaker

-0.49

وبر

-0.49

ULT

-0.48

moor

-0.48

 côtés

-0.47

asen

-0.46

</i>

-0.46

POSITIVE LOGITS

+#+#

0.74

=$?

0.74

expandindo

0.71

<tfoot>

0.71

}{*}{

0.69

 EconPapers

0.69

}{*}{}

0.67

بوابة

0.65

 ویکی‌پدیای

0.63

 pleaſure

0.63

Activations Density 0.047%

programming or technical terminology related to class and method structure

No Comments

No Known Activations