INDEX

Explanations

words related to the processes of categorization and standardization

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 colleg

-0.64

fcntl

-0.61

matchers

-0.61

 beant

-0.56

onuc

-0.55

 orec

-0.55

 Wahr

-0.54

 genel

-0.53

 Schot

-0.53

 thromb

-0.52

POSITIVE LOGITS

ized

1.62

ization

1.53

IZED

1.38

izations

1.35

ised

1.35

ize

1.32

alisation

1.24

IZATION

1.24

ilized

1.21

izing

1.21

Activations Density 0.222%

words related to the processes of categorization and standardization

No Comments

No Known Activations