INDEX

Explanations

negations and expressions of uncertainty or inadequacy

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

"not" followed by an adjective

np_acts-logits-general · gemini-2.0-flash

not known or understood

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

 BoxDecoration

-0.85

MessageTagHelper

-0.81

 autorytatywna

-0.79

 سكانية

-0.77

 Paglinawan

-0.71

 Drapeau

-0.67

+#+#

-0.64

 AssemblyCompany

-0.62

 хоть

-0.62

 Chriftian

-0.61

POSITIVE LOGITS

 fully

1.15

 always

1.08

 entirely

1.04

 necessarily

1.03

 completely

0.97

 sepenuhnya

0.95

 quite

0.90

 Always

0.90

 úplně

0.88

 forcément

0.87

Activations Density 0.603%

negations and expressions of uncertainty or inadequacy

"not" followed by an adjective

not known or understood

No Comments

No Known Activations