INDEX

Explanations

phrases indicating emotional states and personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

Portály

-0.51

éron

-0.49

Normdaten

-0.47

postmedia

-0.46

stateMutability

-0.46

esgue

-0.45

inigte

-0.45

autoIncrement

-0.44

 TextInputType

-0.43

 HttpRequest

-0.42

POSITIVE LOGITS

 AssemblyCulture

0.67

uxxxx

0.67

ArgsConstructor

0.67

 AspNetCore

0.66

stdc

0.62

 Annahme

0.60

躇

0.58

 katal

0.58

 accepting

0.57

InstanceState

0.57

Activations Density 0.342%

phrases indicating emotional states and personal reflections

No Comments

No Known Activations