INDEX

Explanations

terms related to academic context and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

GraphicsUnit

-0.91

تقاوى

-0.77

 MessageBoxIcon

-0.73

 useAppContext

-0.72

 initComponents

-0.72

ngdoc

-0.71

DeleteBehavior

-0.71

 Савезне

-0.70

AccessorTable

-0.69

AsUp

-0.69

POSITIVE LOGITS

 seny

0.42

de

0.41

0.40

 could

0.39

won

0.39

’

0.39

kuuta

0.38

pa

0.38

oa̍t

0.37

↘

0.37

Activations Density 1.334%

terms related to academic context and evaluation

No Comments

No Known Activations