INDEX

Explanations

prominent names and entities related to historical narratives

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

ConstraintMaker

-0.52

 dAtA

-0.51

tagHelperRunner

-0.49

fortawesome

-0.48

AnimationsModule

-0.48

StoryboardSegue

-0.46

ViewFeatures

-0.44

 PyLong

-0.44

 Шта

-0.44

webElementGuid

-0.44

POSITIVE LOGITS

zzleHttp

0.73

rungsseite

0.68

참고

0.65

]}"

0.65

]<<

0.65

 MonoBehaviour

0.63

 Audiodateien

0.59

OrBuilder

0.59

Становништво

0.58

Activations Density 0.918%

prominent names and entities related to historical narratives

No Comments

No Known Activations