INDEX

Explanations

various legal and procedural terminologies and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Mundi

-0.49

eradish

-0.46

UDO

-0.43

relenting

-0.43

谙

-0.43

$__

-0.43

দ্

-0.42

 resultant

-0.42

MIS

-0.41

caccio

-0.41

POSITIVE LOGITS

 referrerpolicy

0.74

 indisponible

0.68

 للمعارف

0.68

 mergeFrom

0.67

UserScript

0.63

PerformLayout

0.63

 BorderSide

0.62

 consultato

0.61

webElementXpaths

0.61

UnsafeEnabled

0.61

Activations Density 0.781%

various legal and procedural terminologies and concepts

No Comments

No Known Activations