INDEX

Explanations

intensifiers and adjectives that convey degrees of magnitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ต่อ

-0.50

HAM

-0.46

 MonoBehaviour

-0.45

enci

-0.45

sel

-0.45

定向

-0.43

iph

-0.42

 pata

-0.42

IBAction

-0.42

ané

-0.41

POSITIVE LOGITS

Jereo

0.98

ViewFeatures

0.92

 AssemblyCulture

0.88

 Мексичка

0.86

 nahilalakip

0.82

ReusableCell

0.79

UrlResolution

0.79

Geplaatst

0.76

 Italijanski

0.76

DebuggerNonUser

0.76

Activations Density 0.271%

intensifiers and adjectives that convey degrees of magnitude

No Comments

No Known Activations