INDEX

Explanations

ellipses or pauses in text, indicating incomplete thoughts or continuations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 Manta

-0.86

 Tasman

-0.79

انت

-0.76

Cly

-0.76

 lordship

-0.76

 Balak

-0.75

 Alderman

-0.75

cetin

-0.74

 Leighton

-0.71

 Dalton

-0.70

POSITIVE LOGITS

 ***!

0.93

 كومونز

0.89

eliness

0.85

uldron

0.85

 Rory

0.84

RenderAtEndOf

0.83

oslav

0.82

Rory

0.81

 resourceCulture

0.81

קישורים

0.80

Activations Density 0.191%

ellipses or pauses in text, indicating incomplete thoughts or continuations

No Comments

No Known Activations