INDEX

Explanations

statements and expressions related to return values in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

FontAwesome

-0.57

 crescere

-0.55

 strerror

-0.53

fortawesome

-0.53

 sacks

-0.53

 EventArgs

-0.48

Drawable

-0.47

 Kingston

-0.46

 BoxFit

-0.46

microbial

-0.45

POSITIVE LOGITS

LabelTagHelper

0.89

GEBURTSDATUM

0.78

 jsPsych

0.77

 useAppContext

0.71

RTLI

0.67

MLLoader

0.67

BeginContext

0.65

 nakalista

0.63

TabStop

0.63

Források

0.62

Activations Density 0.028%

statements and expressions related to return values in code

No Comments

No Known Activations