INDEX

Explanations

specific patterns related to decision-making and different professionals

oai_token-act-pair · gpt-3.5-turbo

phrases related to decision-making and decision-makers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eanor

-0.60

 vulnerability

-0.55

 bankruptcy

-0.53

cture

-0.52

 Alternative

-0.52

 Vanity

-0.52

 airspace

-0.52

 autobiography

-0.51

 Profile

-0.51

 paperback

-0.51

POSITIVE LOGITS

arers

1.47

erers

1.41

ists

1.39

ographers

1.35

makers

1.33

keepers

1.33

agers

1.32

ancers

1.31

icians

1.30

casters

1.29

Activations Density 1.125%

specific patterns related to decision-making and different professionals

phrases related to decision-making and decision-makers

No Comments

No Known Activations