INDEX

Explanations

items or food contaminated with foreign objects

oai_token-act-pair · gpt-3.5-turbo

references to harmful or toxic substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Colleges

-0.67

lished

-0.63

 Marketplace

-0.61

icians

-0.58

soDeliveryDate

-0.57

"]=>

-0.56

 Govern

-0.56

 VIDEOS

-0.56

Requirements

-0.56

eatures

-0.55

POSITIVE LOGITS

idium

0.79

 explosives

0.68

 underwear

0.67

 insign

0.66

 crystals

0.65

oglobin

0.64

 weaponry

0.64

 oxygen

0.63

 jelly

0.62

 attachments

0.62

Activations Density 0.908%

items or food contaminated with foreign objects

references to harmful or toxic substances

No Comments

No Known Activations