INDEX

Explanations

scientific or academic terminology and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 invokingState

-0.59

TagMode

-0.58

 AssemblyCulture

-0.58

 mergeFrom

-0.58

цездатний

-0.57

 Exacts

-0.57

 tartalomajánló

-0.56

 EClass

-0.55

 مؤرشف

-0.55

 للاسماء

-0.52

POSITIVE LOGITS

IsContent

0.60

ंदीखरीदारी

0.56

 también

0.55

 also

0.54

rafa

0.53

 Daya

0.50

Jir

0.50

SizeF

0.50

 TAMBIÉN

0.49

ЛЯ

0.49

Activations Density 1.175%

scientific or academic terminology and references

No Comments

No Known Activations