INDEX

Explanations

specific names of people, places, or organizations related to diverse topics or 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

Насе

-0.73

Personensuche

-0.69

OGND

-0.67

 незавершена

-0.64

SequentialGroup

-0.63

LastError

-0.62

fjspx

-0.61

AccessorTable

-0.61

 LCCN

-0.60

TagMode

-0.60

POSITIVE LOGITS

nonumber

0.51

etc

0.47

Unnamed

0.45

 salta

0.44

 geweest

0.44

osoba

0.44

itettura

0.43

 그리고

0.43

といった

0.43

Activations Density 0.909%

specific names of people, places, or organizations related to diverse topics or contexts

No Comments

No Known Activations