INDEX

Explanations

instances of the term "num" in different contexts

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

]]]

-0.66

Jereo

-0.63

"){

-0.63

++++++++++++++++

-0.62

 Manner

-0.62

hci

-0.60

 AssemblyCompany

-0.59

::::::::::::::::

-0.58

")));

-0.58

":

-0.58

POSITIVE LOGITS

num

2.70

num

2.69

Num

1.97

NUM

1.75

Num

1.75

setNum

1.51

 getNum

1.41

getNum

1.40

NUM

1.38

Nums

1.28

Activations Density 0.037%

instances of the term "num" in different contexts

No Comments

No Known Activations