INDEX

Explanations

numerical values 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 @ 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

MethodManager

-0.49

jgl

-0.43



-0.43

 concrete

-0.42

StrictEqual

-0.41

 ivelany

-0.41

 TestBed

-0.41

WithDefault

-0.41

themselves

-0.39

しまった

-0.38

POSITIVE LOGITS

 مرئيه

0.81

didSet

0.79

脚注の使い方

0.70

 متعلقه

0.67

 AssemblyProduct

0.63

tanleria

0.63

hasia

0.62

 kaarangay

0.60

Попис

0.60

)][

0.59

Activations Density 0.851%

numerical values or references

No Comments

No Known Activations