INDEX

Explanations

references to additional items or concepts in a list or discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 asla

-0.49

ResumeLayout

-0.48

леко

-0.47

unknownFields

-0.45

acia

-0.45

]}"

-0.44

ganggu

-0.43

($__

-0.43

'):

-0.43

"":

-0.42

POSITIVE LOGITS

 cref

0.74

ArgumentParser

0.72

 ComVisible

0.67

 spill

0.66

SharedCtor

0.64

WithFormat

0.62

 digress

0.62

ätzt

0.62

 الدولى

0.61

GOTREF

0.60

Activations Density 0.424%

references to additional items or concepts in a list or discussion

No Comments

No Known Activations