INDEX

Explanations

words and phrases associated with organizational names and research entities

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

цията

-0.48

 świ

-0.43

 opge

-0.43

 Kinney

-0.43

beiros

-0.43

kesmas

-0.42

 Eins

-0.42

len

-0.42

 бо

-0.42

no

-0.42

POSITIVE LOGITS

 الحره

0.85

@[+][

0.81

PyExc

0.81

 Chwiliwch

0.78

SBATCH

0.74

 <>",

0.74

tagHelperRunner

0.73

Enllaços

0.72

bootstrapcdn

0.72

 unknownFields

0.70

Activations Density 2.198%

words and phrases associated with organizational names and research entities

No Comments

No Known Activations