INDEX

Explanations

segments of code or syntax highlighting related to programming structures and elements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoresizingMask

-0.84

MethodManager

-0.67

jsonwebtoken

-0.62

Vorlage

-0.61

InputBorder

-0.61

CppMethod

-0.61

antity

-0.61

forKey

-0.58

readAs

-0.57

AnchorStyles

-0.57

POSITIVE LOGITS

 оригіналу

0.63

)?;

0.60

 himſelf

0.59

 spion

0.59

 Incompatible

0.57

hline

0.57

 perſon

0.56

salms

0.55

].)

0.55

 Chbosky

0.54

Activations Density 0.164%

segments of code or syntax highlighting related to programming structures and elements

No Comments

No Known Activations