INDEX

Explanations

phrases related to entering or going into locations and experiences

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

 estekak

-0.50

rscheinlichkeit

-0.48

mgp

-0.45

agai

-0.44

cui

-0.44

终

-0.43

americanos

-0.43

boretum

-0.43

 élo

-0.42

ூர்

-0.41

POSITIVE LOGITS

 into

1.27

Into

1.25

 Into

1.21

 INTO

1.16

into

1.16

INTO

1.06

 groupBox

0.76

 realm

0.76

 fray

0.75

 depths

0.73

Activations Density 0.196%

phrases related to entering or going into locations and experiences

No Comments

No Known Activations