INDEX

Explanations

phrases indicating the quality and effectiveness of a job or task completed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

worth

-0.45

worthy

-0.44

seh

-0.43

EndOf

-0.42

 something

-0.39

 passen

-0.38

eta

-0.38

 pengh

-0.37

 שוליים

-0.37

IDENTAL

-0.37

POSITIVE LOGITS

 kasarigan

0.79

MessageTagHelper

0.78

findpost

0.78

localctx

0.77

esgue

0.74

 يتيمه

0.74

Jeografia

0.73

 AssemblyCulture

0.73

 AssemblyCompany

0.73

ArrowToggle

0.72

Activations Density 0.174%

phrases indicating the quality and effectiveness of a job or task completed

No Comments

No Known Activations