INDEX

Explanations

words related to materials and their uses in various contexts such as agriculture, manufacturing, and weaponry

oai_token-act-pair · gpt-3.5-turbo

references to materials and their applications

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

 Unsure

-0.80

peer

-0.75

Scope

-0.75

arios

-0.70

pause

-0.70

 Hastings

-0.68

nces

-0.68

Mub

-0.67

details

-0.67

nr

-0.66

POSITIVE LOGITS

 fertil

1.13

 lubric

1.10

 fertilizer

1.09

 manufacture

1.06

 proteins

1.05

 cooking

1.05

 plastics

1.05

 refriger

1.00

 medicines

0.99

dye

0.99

Activations Density 0.347%

words related to materials and their uses in various contexts such as agriculture, manufacturing, and weaponry

references to materials and their applications

No Comments

No Known Activations