INDEX

Explanations

words related to connections or relationships between entities

oai_token-act-pair · gpt-3.5-turbo

references to connections or relationships, particularly those characterized as "ties."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

here

-0.73

erving

-0.71

swer

-0.69

display

-0.68

stall

-0.67

aminer

-0.67

aer

-0.65

horn

-0.65

erve

-0.65

erc

-0.65

POSITIVE LOGITS

 ties

3.96

tie

1.99

 links

1.95

 connections

1.81

 relations

1.54

ties

1.50

Tie

1.44

 relationships

1.43

 contacts

1.42

links

1.37

Activations Density 0.008%

words related to connections or relationships between entities

references to connections or relationships, particularly those characterized as "ties."

No Comments

No Known Activations