INDEX

Explanations

references to locations and geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ModelExpression

-0.82

aarrggbb

-0.74

WriteBarrier

-0.72

AndroidJUnit

-0.70

 autorytatywna

-0.69

StructEnd

-0.68

 pinulongan

-0.67

InstrumentedTest

-0.64

SequentialGroup

-0.63

ThroughAttribute

-0.62

POSITIVE LOGITS

 Brisbane

0.64

 Queensland

0.60

 Ipswich

0.53

 Gold

0.51

bris

0.50

Brisbane

0.49

Queensland

0.49

 Fraser

0.48

qt

0.47

Ips

0.47

Activations Density 0.079%

references to locations and geographic features

No Comments

No Known Activations