INDEX

Explanations

intensely occurring or emphasized concepts, particularly those indicating depth or severity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

PYX

-0.68

Життєпис

-0.57

BeginContext

-0.56

 <<<<<<<<<<<<<<

-0.55

 utafitiHapana

-0.54

िल्

-0.53

AndEndTag

-0.52

PreferredItem

-0.50

tion

-0.49

acaktır

-0.48

POSITIVE LOGITS

 deep

1.76

 DEEP

1.56

 deepest

1.54

 deeper

1.53

deep

1.51

 deepened

1.46

 Deeper

1.46

Deep

1.44

 deepen

1.44

 Deep

1.42

Activations Density 0.088%

intensely occurring or emphasized concepts, particularly those indicating depth or severity

No Comments

No Known Activations