INDEX

Explanations

terms related to "mid" or "middle" as descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 uVar

-0.82

piram

-0.78

олові

-0.78

')]

-0.77

InputBorder

-0.75

ので

-0.74

']")

-0.73

']?>

-0.73

"…

-0.72

blurRadius

-0.72

POSITIVE LOGITS

MID

1.43

mid

1.33

Mid

1.33

Mid

1.32

mid

1.30

MID

1.26

 midwives

1.14

 Midsummer

1.02

 Midtown

1.02

mids

1.00

Activations Density 0.064%

terms related to "mid" or "middle" as descriptors

No Comments

No Known Activations