INDEX

Explanations

terms related to confidentiality and anonymity 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Winaray

-0.70

tadır

-0.61

enumi

-0.60

 oprot

-0.59

LogFactory

-0.59

 CORRE

-0.59

 verwij

-0.58

 rests

-0.57

uete

-0.57

itemBuilder

-0.56

POSITIVE LOGITS

anonymous

0.92

 Designated

0.90

 designated

0.88

Designated

0.83

 anonymous

0.82

 designate

0.75

 Specified

0.75

Anonymous

0.75

designated

0.73

 Anonymous

0.72

Activations Density 0.133%

terms related to confidentiality and anonymity in various contexts

No Comments

No Known Activations