INDEX

Explanations

patterns related to statistical significance in medical or scientific contexts

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

Values or numbers in tables

np_acts-logits-general · gemini-2.0-flash

table categories and content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 مشين

-0.85

脚注の使い方

-0.81

mybatisplus

-0.77

ʺ

-0.68

 населения

-0.67

ResponseStatus

-0.66

Tazama

-0.66

 defStyle

-0.65

SaveChanges

-0.65

 Lynx

-0.64

POSITIVE LOGITS

1.51

0.79

0.69

 coven

0.68

mtliche

0.67

 Guthrie

0.67

ształ

0.67

ariate

0.66

Activations Density 0.058%

patterns related to statistical significance in medical or scientific contexts

Values or numbers in tables

table categories and content

No Comments

No Known Activations