INDEX

Explanations

references to specific medical and biochemical terms along with their conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 betweenstory

-0.74

 بيها

-0.64

 contextLoads

-0.62

 समीक्षक

-0.59

ReadKey

-0.58

RDA

-0.58

]<<"

-0.57

makeText

-0.55

 snippetHide

-0.55

 Certo

-0.54

POSITIVE LOGITS

ٌ

0.68

ものです

0.66

rungsseite

0.64

ล้ว

0.57

 geworden

0.57

onghi

0.56

 AssemblyVersion

0.54

没错

0.54

 geweest

0.52

もので

0.51

Activations Density 0.879%

references to specific medical and biochemical terms along with their conditions

No Comments

No Known Activations