INDEX

Explanations

code segments involving variable assignments or parameter setting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

'):

-0.48

cze

-0.45

"):

-0.41

'){

-0.40

[];

-0.40

 wär

-0.39

too

-0.39

 devons

-0.38

 venons

-0.38

her

-0.38

POSITIVE LOGITS

 false

1.08

false

1.02

 true

1.00

true

1.00

 True

0.93

 False

0.91

True

0.90

False

0.89

 myſelf

0.85

 TRUE

0.81

Activations Density 0.348%

code segments involving variable assignments or parameter setting

No Comments

No Known Activations