INDEX

Explanations

phrases related to physical actions, interactions, and events

oai_token-act-pair · gpt-3.5-turbo

conjunctions that indicate relationships or connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĤ´ãĥ³

-1.02

hered

-0.72

pmwiki

-0.67

NULL

-0.66

ulent

-0.65

 Released

-0.64

Contents

-0.63

inia

-0.63

redd

-0.63

 Â®

-0.62

POSITIVE LOGITS

 everybody

1.34

 stuff

1.29

 blah

1.20

 somebody

1.19

we

1.12

 everything

1.09

 yeah

1.09

1.07

 they

1.03

 then

1.02

Activations Density 0.228%

phrases related to physical actions, interactions, and events

conjunctions that indicate relationships or connections between ideas

No Comments

No Known Activations