INDEX

Explanations

phrases indicating the quality or ranking of experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

lá

-0.52

maro

-0.51

 gili

-0.49

inkas

-0.48

ghs

-0.47

 celu

-0.46

ple

-0.46

brus

-0.46

PLE

-0.46

 supersede

-0.45

POSITIVE LOGITS

 nahilalakip

0.82

Geplaatst

0.79

MigrationBuilder

0.74

DockStyle

0.74

findpost

0.71

 оригіналу

0.71

setVerticalGroup

0.69

 Christendom

0.67

kháu

0.67

mybatisplus

0.65

Activations Density 0.236%

phrases indicating the quality or ranking of experiences

No Comments

No Known Activations