INDEX

Explanations

references to inclusion or integration in various contexts

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

<eos>

-0.58

 Every

-0.49

ked

-0.47

ApiModel

-0.47

nen

-0.46

 فل

-0.46

脚注の使い方

-0.46

JAH

-0.45

Every

-0.44

zie

-0.44

POSITIVE LOGITS

rungsseite

1.07

 дописавши

0.95

Hozzáférés

0.85

addGroup

0.82

AnchorStyles

0.81

 وتسجيلات

0.76

 مشين

0.75

TagMode

0.74

 חיצוניים

0.72

وردار

0.69

Activations Density 0.004%

references to inclusion or integration in various contexts

No Comments

No Known Activations