INDEX

Explanations

terms related to regulatory and legal contexts, particularly in healthcare and finance

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

preceding mathematical symbols

np_acts-logits-general · gemini-2.0-flash

technical and mathematical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

+#+#

-0.81

providedIn

-0.75

fromCharCode

-0.72

-0.71

Slf

-0.71

-0.70

-0.68

jspx

-0.67

-0.66

POSITIVE LOGITS

 themſelves

1.26

 myſelf

1.20

 Theſe

1.18

 himſelf

1.16

 whoſe

1.11

Efq

1.09

 becauſe

1.08

 doubtnut

1.05

 itſelf

1.04

 Monfieur

1.00

Activations Density 4.240%

terms related to regulatory and legal contexts, particularly in healthcare and finance

preceding mathematical symbols

technical and mathematical terms

No Comments

No Known Activations