INDEX

Explanations

phrases and terms related to names, titles, and languages

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

complexContent

-0.58

TargetException

-0.57

حوالہ

-0.51

formik

-0.47

oa̍t

-0.47

$_['

-0.46

ContentAsync

-0.45

 vsak

-0.44

ImageContext

-0.43

OrNil

-0.42

POSITIVE LOGITS

 pronunciation

0.79

 spelling

0.79

 spellings

0.72

 pronouncing

0.69

 pronon

0.66

 pronunci

0.63

 spelled

0.61

 &___

0.61

 representation

0.59

 pronounce

0.57

Activations Density 0.709%

phrases and terms related to names, titles, and languages

No Comments

No Known Activations