INDEX

Explanations

words related to feedback, communication, and community engagement

oai_token-act-pair · gpt-3.5-turbo

phrases related to communication and interaction difficulties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

istries

-0.79

Brexit

-0.74

agate

-0.74

TPP

-0.73

ramid

-0.73

iberal

-0.71

£ı

-0.70

urgical

-0.70

aclysm

-0.69

tesque

-0.68

POSITIVE LOGITS

 passers

1.59

 spectators

1.55

 onlook

1.53

 attendees

1.38

 teammates

1.38

 guests

1.37

 viewers

1.35

 bystanders

1.32

 listeners

1.30

 patrons

1.27

Activations Density 0.424%

words related to feedback, communication, and community engagement

phrases related to communication and interaction difficulties

No Comments

No Known Activations