INDEX

Explanations

the presence of initial indicators or signals of new topics or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

anen

-0.66

rens

-0.65

iques

-0.63

Читати

-0.60

mêmes

-0.59

 vore

-0.59

opa

-0.59

 NOVA

-0.59

ため

-0.59

يميديا

-0.59

POSITIVE LOGITS

addGap

0.78

cshtml

0.76

InjectAttribute

0.75

 дописавши

0.73

eqn

0.71

ribune

0.67

illance

0.67

SizeF

0.66

 EClass

0.66

MemoryWarning

0.65

Activations Density 0.025%

the presence of initial indicators or signals of new topics or concepts

No Comments

No Known Activations