INDEX

Explanations

references to scientific and medical research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 hlavy

-0.70

ýš

-0.68

లాలు

-0.57

naph

-0.56

بالإنجليزية

-0.56

 vlasy

-0.55

paravant

-0.55

ulipas

-0.55

naphthal

-0.55

 coasts

-0.54

POSITIVE LOGITS

 "..\..\..\

0.67

 "..\..\

0.63

TextHelper

0.63

TargetException

0.61

 виправивши

0.61

Odkazy

0.60

tagHelper

0.57

antMatchers

0.56

Ok

0.55

ว์

0.54

Activations Density 0.187%

references to scientific and medical research contexts

No Comments

No Known Activations

references to scientific and medical research contexts

No Comments

No Known Activations