INDEX

Explanations

phrases indicating significant negative impact or consequence

oai_token-act-pair · gpt-3.5-turbo

negative impacts and their effects on various groups or entities

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

NESS

-0.69

wine

-0.67

 mutated

-0.66

 whore

-0.63

fw

-0.62

 atro

-0.60

 supplied

-0.60

cles

-0.59

 rods

-0.58

qi

-0.58

POSITIVE LOGITS

 morale

0.77

 welf

0.69

ãĤ®

0.66

 campaigners

0.64

 whistle

0.62

 whistlebl

0.62

 Palestin

0.62

ibaba

0.62

vae

0.62

warts

0.62

Activations Density 0.182%

phrases indicating significant negative impact or consequence

negative impacts and their effects on various groups or entities

No Comments

No Known Activations