INDEX

Explanations

phrases that indicate varying conditions or categories

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

<?

-0.51

berry

-0.46

̍t

-0.45

IUrlHelper

-0.45

^{-

-0.44

さえ

-0.43

&'

-0.43

ότητα

-0.42

letus

-0.42

 stessi

-0.42

POSITIVE LOGITS

 different

2.00

different

1.79

 varying

1.78

Different

1.75

 Different

1.68

 differing

1.52

 unterschied

1.50

 diferentes

1.49

 DIFFERENT

1.45

不同的

1.41

Activations Density 1.264%

phrases that indicate varying conditions or categories

No Comments

No Known Activations