INDEX

Explanations

terms related to interpolation and data structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.67

CloseOperation

-0.60

 مشين

-0.53

rold

-0.51

 Alfred

-0.50

Hew

-0.50

prehen

-0.49

merie

-0.49

ViewFeatures

-0.49

ggak

-0.48

POSITIVE LOGITS

osoba

0.63

Autoritní

0.61

onomía

0.59

 PeEnEo

0.58

￡

0.57

 veckor

0.57

onomia

0.56

PhysRev

0.55

 pageContext

0.55

 раду

0.54

Activations Density 0.529%

terms related to interpolation and data structures

No Comments

No Known Activations