INDEX

Explanations

questions and inquiries aimed at understanding problems or solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

BASEPATH

-0.65

 Cosmos

-0.57

UseVisualStyle

-0.57

ыгана

-0.51

')],

-0.48

 guste

-0.48

"}}>

-0.48

'}}>

-0.47

anInt

-0.47

getMenuInflater

-0.46

POSITIVE LOGITS

зулта

0.80

CloseOperation

0.72

？

0.68

RuleContext

0.67

UnitTesting

0.65

؟

0.63

phthal

0.63

DoubleQuotes

0.62

 stump

0.57

Activations Density 0.530%

questions and inquiries aimed at understanding problems or solutions

No Comments

No Known Activations