INDEX

Explanations

specific addresses and locations

oai_token-act-pair · gpt-3.5-turbo

specific addresses and location-related details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 realised

-0.81

 analysed

-0.80

 Canaver

-0.78

 apologise

-0.78

 organising

-0.77

 learnt

-0.77

 hitherto

-0.75

ana

-0.75

 Nasa

-0.72

 interrog

-0.72

POSITIVE LOGITS

 Avenue

1.25

 Boulevard

1.24

 Creek

1.22

 Blvd

1.16

vale

1.13

 Plaza

1.11

 Grove

1.09

 Lakes

1.07

 Junction

1.06

 Parkway

1.05

Activations Density 0.331%

specific addresses and locations

specific addresses and location-related details

No Comments

No Known Activations