INDEX

Explanations

terms related to prior actions or conditions in legal and technical contexts

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

preceding "to"

np_acts-logits-general · gemini-2.0-flash

contrary to and prior to

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

 kasarigan

-0.92

 defaultstate

-0.90

InSection

-0.81

WebVitals

-0.79

WillAppear

-0.78

 AssemblyCompany

-0.77

WEBPACK

-0.77

ItemBackground

-0.76

原始内容存档于

-0.72

ftagPool

-0.71

POSITIVE LOGITS

to

1.98

 thereto

1.51

tothe

1.38

 kepada

1.35

到

1.15

к

1.07

 unto

1.07

 vnto

1.01

tot

0.96

aux

0.95

Activations Density 1.139%

terms related to prior actions or conditions in legal and technical contexts

preceding "to"

contrary to and prior to

No Comments

No Known Activations