INDEX

Explanations

terms related to addiction and associated concepts such as treatment, recovery, and effects

oai_token-act-pair · gpt-3.5-turbo

terms related to addiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Kov

-0.85

erial

-0.73

prints

-0.68

stand

-0.67

eor

-0.66

vard

-0.65

printed

-0.65

peed

-0.64

 Gael

-0.63

DIR

-0.63

POSITIVE LOGITS

 addiction

1.03

 addict

0.93

 relapse

0.93

 addicted

0.91

encies

0.90

 Addiction

0.87

 rehab

0.86

icts

0.85

 craving

0.85

olescent

0.81

Activations Density 0.028%

terms related to addiction and associated concepts such as treatment, recovery, and effects

terms related to addiction

No Comments

No Known Activations