INDEX

Explanations

words related to law enforcement activities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Kraft

-0.83

sonian

-0.78

resents

-0.77

 Centauri

-0.76

 Elon

-0.74

 Remastered

-0.73

 Ascension

-0.72

ospel

-0.69

Zot

-0.69

 Ender

-0.68

POSITIVE LOGITS

 patrols

1.64

 patrolling

1.60

 patrol

1.52

 arresting

1.46

 policing

1.45

 crackdown

1.33

 enforcement

1.33

 apprehend

1.32

 arrests

1.32

 enforcing

1.30

Activations Density 0.607%

words related to law enforcement activities

No Comments

No Known Activations