INDEX

Explanations

the word "position" in various contexts

oai_token-act-pair · gpt-4-turbo

specific positions or locations within a context

oai_token-act-pair · gpt-3.5-turbo

references to positional information or positioning in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ebook

-0.75

bey

-0.74

ilee

-0.72

vous

-0.69

 Flavoring

-0.68

ħĭ

-0.67

displayText

-0.67

burn

-0.65

Interstitial

-0.65

rd

-0.64

POSITIVE LOGITS

position

0.98

 position

0.95

 positions

0.93

ession

0.82

Position

0.79

itions

0.79

 orientation

0.76

ngth

0.75

 Position

0.73

 locations

0.72

Activations Density 0.029%

the word "position" in various contexts

specific positions or locations within a context

references to positional information or positioning in various contexts

No Comments

No Known Activations