INDEX

Explanations

words related to puppets and strings

oai_token-act-pair · gpt-3.5-turbo

references to puppets or puppet-related concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Scotia

-0.73

 Fukushima

-0.72

 variance

-0.72

 logger

-0.65

ãĥ³ãĤ¸

-0.64

 Goods

-0.63

âĵĺ

-0.63

FTWARE

-0.62

 saline

-0.62

 Aberdeen

-0.62

POSITIVE LOGITS

etry

1.30

etooth

1.12

ety

1.10

eling

1.09

ete

1.03

ees

1.03

essee

1.03

ellery

1.02

etary

0.96

ormal

0.95

Activations Density 0.111%

words related to puppets and strings

references to puppets or puppet-related concepts

No Comments

No Known Activations