INDEX

Explanations

references to validation and evidence in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 ricca

-0.53

 næste

-0.52

WebElementEntity

-0.51

croix

-0.49

 prossima

-0.47

iados

-0.47

ificent

-0.47

 válvula

-0.47

ROLS

-0.46

ricate

-0.45

POSITIVE LOGITS

DoubleQuotes

0.65

MemoryWarning

0.63

 Egli

0.61

 autorytatywna

0.60

 assumes

0.60

 CreateTagHelper

0.59

Datuak

0.59

 purpoſe

0.59

 createContext

0.57

Activations Density 0.927%

references to validation and evidence in research contexts

No Comments

No Known Activations