INDEX

Explanations

mentions of the name "Sydney"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Sydney."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Ã§a

-0.67

 deaf

-0.66

voy

-0.64

Xi

-0.63

 pity

-0.60

 resolve

-0.60

TAIN

-0.60

 FIRE

-0.60

 caution

-0.59

TRY

-0.58

POSITIVE LOGITS

roxy

1.09

roid

1.08

aniel

1.06

rox

1.03

essert

0.98

ynamic

0.93

imentary

0.93

ere

0.93

ritch

0.93

ynam

0.90

Activations Density 0.010%

mentions of the name "Sydney"

references to the term "Sydney."

No Comments

No Known Activations