INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'R' followed by the number 2, indicating it is looking for references to R2

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cart

-0.69

 Pose

-0.65

terson

-0.64

 Schumer

-0.64

 regards

-0.63

 pear

-0.62

 vein

-0.61

 yours

-0.61

grass

-0.61

CPR

-0.61

POSITIVE LOGITS

ansom

1.43

haps

1.36

otten

1.35

outine

1.32

itchie

1.31

ascal

1.26

ifles

1.21

uling

1.20

otation

1.18

ework

1.17

Activations Density 0.044%

proper nouns

instances of the letter 'R' followed by the number 2, indicating it is looking for references to R2

No Comments

No Known Activations