INDEX

Explanations

phrases related to data organization and structure

oai_token-act-pair · gpt-3.5-turbo

references to gender classifications

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

––

-0.65

Instead

-0.64

—-

-0.63

biz

-0.60

Luckily

-0.58

Ì¶

-0.58

something

-0.57

Thankfully

-0.57

Truth

-0.57

 âĢķ

-0.56

POSITIVE LOGITS

 phylogen

0.70

 numbering

0.65

 hapl

0.64

 annotation

0.63

 Leica

0.60

 variants

0.60

 alle

0.60

osate

0.60

 allele

0.60

 Lists

0.60

Activations Density 2.142%

phrases related to data organization and structure

references to gender classifications

No Comments

No Known Activations