INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Ron."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 rigging

-0.66

LER

-0.64

ready

-0.62

cy

-0.61

 seeded

-0.59

 sympathetic

-0.58

 chance

-0.57

 warrants

-0.56

 warrant

-0.56

enegger

-0.55

POSITIVE LOGITS

ald

1.19

aldo

1.17

nie

0.99

ny

0.96

 Swanson

0.91

nen

0.89

ni

0.88

Paul

0.88

imo

0.86

 Weasley

0.85

Activations Density 0.024%

proper nouns

mentions of the name "Ron."

No Comments

No Known Activations