INDEX

Explanations

references to quantities or measurements described in a specific context

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

…

-0.49

<eos>

-0.49

…

-0.46

err

-0.45

 समीक्षाएं

-0.45

epi

-0.45

 would

-0.43

indic

-0.43

,…

-0.43

 bár

-0.41

POSITIVE LOGITS

LookAnd

0.95

 nakalista

0.83

'])){

0.80

ніципа

0.80

Geplaatst

0.79

insee

0.78

']))

0.75

 distanciation

0.75

UnsafeEnabled

0.74

")));

0.73

Activations Density 1.467%

references to quantities or measurements described in a specific context

No Comments

No Known Activations