INDEX

Explanations

terms related to enrichment and enhancement in various contexts

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

Word fragment "Enrichment" and variants

np_acts-logits-general · gemini-2.0-flash

enrichment analysis or encoding

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WindowConstants

-0.74

abestanden

-0.71

pyplot

-0.63

mW

-0.60

scc

-0.55

TOMS

-0.55

istock

-0.55

 usus

-0.53

 Injectable

-0.52

Viki

-0.52

POSITIVE LOGITS

 незавершена

0.77

 Enid

0.70

Eno

0.69

ment

0.65

enc

0.64

ments

0.63

 Ennis

0.61

."</

0.61

RestTemplate

0.60

kloped

0.60

Activations Density 0.146%

terms related to enrichment and enhancement in various contexts

Word fragment "Enrichment" and variants

enrichment analysis or encoding

No Comments

No Known Activations