INDEX

Explanations

mentions of bots and verification-related terms associated with misinformation and identification

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

Obrázky

-0.80

mybatisplus

-0.69

PerformLayout

-0.65

MetaObject

-0.64

 بيها

-0.61

 typelib

-0.61

</tfoot>

-0.59

)|^{

-0.59

\|_{

-0.58

 puissiez

-0.57

POSITIVE LOGITS

DeleteBehavior

0.69

God

0.52

uding

0.50

adpleegd

0.49

 either

0.48

ToBounds

0.48

 étranger

0.47

嚟

0.46

ftagPool

0.46

rungsseite

0.46

Activations Density 0.580%

mentions of bots and verification-related terms associated with misinformation and identification

No Comments

No Known Activations