INDEX

Explanations

instances of numerical values

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

########.

-0.77

]]

-0.74

ГЛА

-0.70

 transfieras

-0.69

تقاوى

-0.68

 Paglinawan

-0.68

 Blok

-0.67

 متعلقه

-0.66

 Dati

-0.66

]>=

-0.66

POSITIVE LOGITS

 २०

0.80

AndEndTag

0.79

 ২০

0.68

wanzig

0.68

 veinte

0.67

 coscienza

0.66

entieth

0.65

Ath

0.64

 vzduchu

0.64

Activations Density 0.208%

instances of numerical values

No Comments

No Known Activations