INDEX

Explanations

names of places and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-0.65

 itſelf

-0.64

 astore

-0.61

 myſelf

-0.60

 houſe

-0.56

 Infórmanos

-0.56

clusal

-0.55

MENAFN

-0.53

UnsafeEnabled

-0.51

farb

-0.51

POSITIVE LOGITS

 Greek

1.04

 Greece

0.99

Greek

0.93

 Thessaloniki

0.91

Greece

0.90

 greek

0.88

 Hellenic

0.87

 Athens

0.82

 GREEK

0.82

greek

0.78

Activations Density 0.097%

names of places and geographical locations

No Comments

No Known Activations