INDEX

Explanations

references to legal terminology or specific case citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SpringBootTest

-0.74

 antar

-0.65

 reger

-0.63

 Holtz

-0.62

 Bloch

-0.61

hik

-0.59

(`

-0.59

 purpoſe

-0.59

 adat

-0.59

 Ariel

-0.59

POSITIVE LOGITS

pa

2.79

Pa

2.76

Pa

2.72

pa

2.69

PA

2.62

PA

2.61

 Paxton

1.57

PAI

1.51

Pao

1.51

 Pennsylvania

1.44

Activations Density 0.114%

references to legal terminology or specific case citations

No Comments

No Known Activations