INDEX

Explanations

ellipses and punctuation indicating pauses or unfinished thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

CppMethod

-0.93

-0.90

ﬃ

-0.88

RunAsync

-0.85

tonsoft

-0.84

⁠

-0.83

+"'

-0.80

∘

-0.80

\[

-0.78

例文帳に追加

-0.77

POSITIVE LOGITS

..

2.05

)..

1.80

..

1.76

"..

1.41

..(

1.41

..”

1.40

'..

1.38

.."

1.37

..\

1.31

..)

1.24

Activations Density 0.152%

ellipses and punctuation indicating pauses or unfinished thoughts

No Comments

No Known Activations