INDEX

Explanations

words related to spices, particularly cumin

oai_token-act-pair · gpt-3.5-turbo

references to the spice cumin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 autonomy

-0.75

izoph

-0.71

 shenan

-0.66

cffff

-0.63

 bargaining

-0.62

ERSON

-0.58

 millennium

-0.58

 Immunity

-0.58

Kings

-0.57

 bodily

-0.57

POSITIVE LOGITS

umin

1.26

osity

1.21

ous

1.16

ously

1.12

ations

1.03

atus

0.98

urnal

0.95

atis

0.90

ates

0.90

ographed

0.89

Activations Density 0.008%

words related to spices, particularly cumin

references to the spice cumin

No Comments

No Known Activations