INDEX

Explanations

locations and geographical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

styleType

-0.69

 nahilalakip

-0.66

EndProject

-0.63

 Normdatei

-0.62

 Chwiliwch

-0.58

UnsafeEnabled

-0.56

quium

-0.54

Rujuakan

-0.52

 beginnetje

-0.52

 kaynağından

-0.52

POSITIVE LOGITS

zwald

0.68

 Fordham

0.63

 Sligo

0.59

 Kilkenny

0.57

 Freezer

0.56

 Nantucket

0.56

typeorm

0.56

startswith

0.56

 Algarve

0.55

 >=",

0.55

Activations Density 0.246%

locations and geographical references

No Comments

No Known Activations