INDEX

Explanations

references to historical events and time periods

oai_token-act-pair · gpt-3.5-turbo

references to ancient historical periods and dates

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

cipled

-0.90

NESS

-0.77

 Ally

-0.77

 hurting

-0.74

 VMware

-0.73

 Comcast

-0.73

 Blaster

-0.72

 Tonight

-0.69

committee

-0.69

 hurts

-0.69

POSITIVE LOGITS

 Archae

1.20

 archae

1.14

 Egyptians

1.13

Ancient

1.11

 civilisation

1.10

 civilizations

1.09

 archaeological

1.09

 ancestor

1.08

 Antiqu

1.08

 Zoro

1.07

Activations Density 0.849%

references to historical events and time periods

references to ancient historical periods and dates

No Comments

No Known Activations