INDEX

Explanations

phrases related to specific terms in a formal or structured context

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 augus

-0.65

 aproveitar

-0.59

roh

-0.59

 karte

-0.57

<bos>

-0.56

 gani

-0.56

 makro

-0.55

 guma

-0.55

 kard

-0.54

 Profes

-0.54

POSITIVE LOGITS

 xPos

0.89

 posX

0.82

 newVal

0.78

 retVal

0.73

 errorMsg

0.69

 newArr

0.68

 userInput

0.67

 rowCount

0.66

 ecru

0.65

 nodeId

0.65

Activations Density 0.693%

phrases related to specific terms in a formal or structured context

No Comments

No Known Activations