INDEX

Explanations

terms related to eligibility criteria 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

 Greenpeace

-0.72

клопе

-0.70

存于互联网档案馆

-0.67

blurRadius

-0.67

findpost

-0.66

 preſent

-0.64

 poffible

-0.63

éez

-0.61

VIAF

-0.60

 estimés

-0.60

POSITIVE LOGITS

 tier

0.99

Tier

0.95

 Tier

0.94

 مرئيه

0.81

tier

0.76

 tiers

0.70

 pretty

0.69

TIER

0.64

equity

0.64

 equity

0.62

Activations Density 0.079%

terms related to eligibility criteria in various contexts

No Comments

No Known Activations