INDEX

Explanations

references to academic presses and institutions

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

 itſelf

-0.71

 kaarangay

-0.67

TestBed

-0.67

 للاسماء

-0.65

 mergeFrom

-0.65

 myſelf

-0.64

 TestBed

-0.62

 समीक्षाओं

-0.62

 ComVisible

-0.62

 Bekasi

-0.61

POSITIVE LOGITS

Verlag

0.49

 Press

0.47

новништво

0.46

CrossRef

0.44

Press

0.43

grà

0.42

ansha

0.42

 publishers

0.41

role

0.40

 estre

0.40

Activations Density 0.331%

references to academic presses and institutions

No Comments

No Known Activations