INDEX

Explanations

numerical values associated with programming or technical parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.78

 שוליים

-0.74

حياته

-0.69

حياتها

-0.69

elemField

-0.68

 useParams

-0.67

antMatchers

-0.67

mergeFrom

-0.66

ExtendWith

-0.65

Cyfeiriadau

-0.63

POSITIVE LOGITS

↵↵

0.88

</table>

0.66

<eos>

0.65

↵↵↵↵↵↵

0.64

↵↵↵↵

0.61

↵↵↵

0.59

illotine

0.58

 Paused

0.58

.)}

0.56

Sidenav

0.55

Activations Density 0.105%

numerical values associated with programming or technical parameters

No Comments

No Known Activations