INDEX

Explanations

concepts related to quantification and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Trama

-0.59

-0.57

böz

-0.51

letcher

-0.47

اعده

-0.46

 nonatomic

-0.45

pushFollow

-0.45

koma

-0.45

 Tomar

-0.45

weł

-0.44

POSITIVE LOGITS

ity

1.37

ITY

1.17

ities

1.16

ity

1.04

itys

0.99

idad

0.96

ties

0.95

idade

0.95

ITIES

0.93

ty

0.86

Activations Density 0.238%

concepts related to quantification and measurement

No Comments

No Known Activations