INDEX

Explanations

specific proper nouns and references to individuals or entities

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

 OMITBAD

-0.83

ázaro

-0.74

DockStyle

-0.73

RefNanny

-0.72

setVerticalGroup

-0.70

OGND

-0.68

ThroughAttribute

-0.68

 PhpStorm

-0.67

ConstraintMaker

-0.66

+#+#

-0.66

POSITIVE LOGITS

<bos>

0.85

 насељу

0.54

 kasarigan

0.47

 fallait

0.47

 faut

0.46

atini

0.42

transQ

0.41

InputLabel

0.41

isSuccessful

0.41

PreferredItem

0.41

Activations Density 2.580%

specific proper nouns and references to individuals or entities

No Comments

No Known Activations