INDEX

Explanations

numerical values and transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 autorytatywna

-0.87

՚

-0.84

¦

-0.83

 chi̍t

-0.79

 Majefty

-0.78

…

-0.78

ſelves

-0.75

…~

-0.75

 …)

-0.74

AddTagHelper

-0.74

POSITIVE LOGITS

--

0.71

--

0.69

...

0.69

0.65

....

0.60

---

0.58

 postIndex

0.56

（

0.55

</code>

0.54

'--

0.54

Activations Density 0.181%

numerical values and transitions

No Comments

No Known Activations