INDEX

Explanations

references to geographical locations or countries

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

addContainerGap

-0.70

iotensin

-0.60

 linkovi

-0.57

发表于

-0.55

 noDo

-0.54

 SearchView

-0.53

ylase

-0.53

amins

-0.52

wardship

-0.52

icza

-0.51

POSITIVE LOGITS

 initComponents

0.73

 mainland

0.70

 CanadaChoose

0.69

 HasFactory

0.67

 Meksiku

0.66

UnusedPrivate

0.66

>{@

0.60

GraphicsUnit

0.59

LookAnd

0.59

 AssemblyProduct

0.57

Activations Density 0.582%

references to geographical locations or countries

No Comments

No Known Activations