INDEX

Explanations

proper nouns, specifically names of authors, researchers, or individuals often associated with academic publications or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

IBOutlet

-0.65

 OnInit

-0.60

IBAction

-0.60

Diweddarwch

-0.59

 onCreateView

-0.56

 ['./

-0.56

IsContent

-0.55

 saying

-0.53

noinspection

-0.53

the

-0.52

POSITIVE LOGITS

TagHelper

0.67

TagMode

0.63

 Maladies

0.57

recated

0.56

ionine

0.55

 mobilisation

0.53

 Wiktionnaire

0.50

 mobilization

0.48

 uintptr

0.48

 nanotubes

0.48

Activations Density 0.180%

proper nouns, specifically names of authors, researchers, or individuals often associated with academic publications or references

No Comments

No Known Activations