INDEX

Explanations

phrases related to actions and consequences

oai_token-act-pair · gpt-3.5-turbo

concepts related to well-being and social responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disadvant

-0.52

 Sutherland

-0.51

 Azerb

-0.50

DonaldTrump

-0.50

 Aval

-0.47

 Seym

-0.47

ibrary

-0.46

yip

-0.46

gerald

-0.45

 Moroc

-0.44

POSITIVE LOGITS

 thereof

1.08

 thereto

0.97

 thereafter

0.95

 alike

0.91

 accordingly

0.91

 therein

0.81

 versa

0.69

cellaneous

0.62

 afterward

0.62

 afterwards

0.62

Activations Density 1.994%

phrases related to actions and consequences

concepts related to well-being and social responsibility

No Comments

No Known Activations