INDEX

Explanations

references to list indexing and iteration

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

]>=

-0.80

]<=

-0.76

Autoritní

-0.72

oa̍t

-0.67

RenderAtEndOf

-0.67

 Chwiliwch

-0.66

].(

-0.64

 autorytatywna

-0.63

)<=

-0.63

 betweenstory

-0.61

POSITIVE LOGITS

initComponents

0.67

IntoConstraints

0.63

0.54

 pozi

0.52

npos

0.52

𝑗

0.51

importanza

0.51

 iParam

0.51

 cirque

0.50

ManagedBean

0.50

Activations Density 0.611%

references to list indexing and iteration

No Comments

No Known Activations