INDEX

Explanations

unique programming constructs and references related to data manipulation and abstraction

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

 برانيه

-0.79

parsedMessage

-0.67

Попис

-0.61

PreferredItem

-0.59

 EconPapers

-0.58

 }^{*}

-0.57

expandindo

-0.56

ineno

-0.55

withOpacity

-0.54

 defaultstate

-0.54

POSITIVE LOGITS

Portail

0.68

 pleaſure

0.67

 Monfieur

0.64

ſelf

0.62

 leaſt

0.61

 poffible

0.58

 ſmall

0.56

uſ

0.55

 iſt

0.54

ſelves

0.54

Activations Density 0.148%

unique programming constructs and references related to data manipulation and abstraction

No Comments

No Known Activations