INDEX

Explanations

code structures and elements related to class definitions in programming

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

 الرياضيه

-0.72

SizeMode

-0.66

aculture

-0.61

 فريبيس

-0.60

AccessorTable

-0.57

oubliez

-0.57

 CURLOPT

-0.56

itattu

-0.55

rubin

-0.55

amoja

-0.55

POSITIVE LOGITS

ⓧ

0.65

expandindo

0.59

 fallu

0.55

 énergétique

0.51

 nucléaire

0.51

.*")]

0.50

 Elbow

0.49

jaw

0.49

 douce

0.48

Rüyada

0.47

Activations Density 0.018%

code structures and elements related to class definitions in programming

No Comments

No Known Activations