INDEX

Explanations

proper nouns, specifically names of individuals and contributors

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

="@+

-0.55

 poveznice

-0.52

tinyos

-0.49

 estekak

-0.47

rrggbb

-0.47

cshtml

-0.47

 linkovi

-0.47

CppCodeGen

-0.46

 nakalista

-0.46

CodedInputStream

-0.45

POSITIVE LOGITS

quelize

0.68

webElementXpaths

0.67

 perpetuity

0.62

 Mexique

0.57

 nôtre

0.57

 cérémonie

0.57



0.56

 sœur

0.56

)*/

0.55

 Corée

0.55

Activations Density 0.183%

proper nouns, specifically names of individuals and contributors

No Comments

No Known Activations