INDEX

Explanations

mentions of news organizations or media outlets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

BufferException

-0.58

 représ

-0.56

 particuliers

-0.55

<bos>

-0.55

yntaxException

-0.54

 ComVisible

-0.53

complexContent

-0.52

 gainera

-0.51

 dAtA

-0.51

 resultó

-0.50

POSITIVE LOGITS

tvguidetime

1.24

########.

1.11

PRNewswire

1.05

+#+#

0.91

 utafitiHapana

0.90

ंदीखरीदारी

0.86

ագրություններ

0.81

DotNetBar

0.77

expandindo

0.77

 EconPapers

0.77

Activations Density 0.051%

mentions of news organizations or media outlets

No Comments

No Known Activations