INDEX

Explanations

instances of the word "EM" followed by a number

oai_token-act-pair · gpt-3.5-turbo

repeated references or mentions of the term "Em."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Kubrick

-0.75

 Icelandic

-0.70

ASC

-0.69

 Iceland

-0.68

 Idle

-0.67

ãģį

-0.65

 trout

-0.63

 Elves

-0.63

aird

-0.62

 Ancients

-0.62

POSITIVE LOGITS

phasis

1.42

otional

1.31

otions

1.30

otion

1.26

brace

1.22

igrant

1.21

phas

1.15

igrants

1.13

issions

1.12

otive

1.11

Activations Density 0.017%

instances of the word "EM" followed by a number

repeated references or mentions of the term "Em."

No Comments

No Known Activations