INDEX

Explanations

phrases related to physical connections or relationships

oai_token-act-pair · gpt-3.5-turbo

terms related to connectivity and linking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cheat

-0.72

 attendant

-0.69

disk

-0.63

Ĥİ

-0.61

hra

-0.60

fl

-0.60

sv

-0.60

ached

-0.59

 meantime

-0.58

cover

-0.58

POSITIVE LOGITS

 dots

0.99

 seamlessly

0.80

links

0.71

ELF

0.68

 Rivals

0.67

 them

0.67

 Blackwell

0.66

 disparate

0.66

 sexes

0.66

anooga

0.65

Activations Density 0.061%

phrases related to physical connections or relationships

terms related to connectivity and linking

No Comments

No Known Activations