INDEX

Explanations

titles or headings within text

oai_token-act-pair · gpt-3.5-turbo

references to titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Spice

-0.75

ratom

-0.69

gm

-0.68

ombo

-0.65

 Leone

-0.63

apons

-0.62

 fortun

-0.61

onz

-0.61

inces

-0.60

istani

-0.60

POSITIVE LOGITS

manship

0.94

holder

0.88

marks

0.86

plates

0.85

plate

0.84

card

0.84

holders

0.83

 sponsor

0.81

pad

0.80

 deeds

0.79

Activations Density 0.039%

titles or headings within text

references to titles

No Comments

No Known Activations