INDEX

Explanations

words related to expressing thoughts and opinions

oai_token-act-pair · gpt-3.5-turbo

expressions of personal agency and emotional experiences

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

 themselves

-0.67

 apiece

-0.64

 respectively

-0.63

idates

-0.60

Their

-0.57

 tariffs

-0.51

 turnover

-0.51

Us

-0.50

idges

-0.49

 populous

-0.48

POSITIVE LOGITS

 myself

1.88

my

1.39

My

0.89

MY

0.86

my

0.83

My

0.83

 blogging

0.74

 mine

0.74

am

0.70

0.67

Activations Density 1.211%

words related to expressing thoughts and opinions

expressions of personal agency and emotional experiences

No Comments

No Known Activations