INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Ö

-0.61

Interested

-0.59

lihood

-0.58

-0.55

uminati

-0.55

https

-0.54

ettle

-0.54

berra

-0.53

 ..."

-0.52

_-_

-0.51

POSITIVE LOGITS

 heirs

0.62

 added

0.61

added

0.61

 prevailed

0.61

 spokeswoman

0.60

 spokesman

0.59

 conceded

0.58

 lamented

0.56

 boasted

0.56

 admitted

0.55

Activations Density 0.910%

people's names

proper nouns, specifically names of people

No Comments

No Known Activations