INDEX

Explanations

questions or uncertainties about standards and protocols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

^(@)

-0.74

 Monfieur

-0.73

Efq

-0.72

$_"

-0.72

 Theſe

-0.69

 ―――――

-0.68

 iſt

-0.67

 pinulongan

-0.66

 auffi

-0.65

mphony

-0.65

POSITIVE LOGITS

Why

0.51

 utafitiHapana

0.49

WHY

0.48

 mergeFrom

0.47

why

0.47

Why

0.47

mės

0.46

atst

0.45

why

0.44

Bronnen

0.43

Activations Density 0.392%

questions or uncertainties about standards and protocols

No Comments

No Known Activations