INDEX

Explanations

phrases related to potential risks or issues

oai_token-act-pair · gpt-3.5-turbo

phrases or concepts related to uncertainty and risk

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

regor

-0.86

anamo

-0.77

uay

-0.67

xus

-0.67

raltar

-0.65

uberty

-0.63

adelphia

-0.62

othal

-0.60

 Britann

-0.60

vation

-0.59

POSITIVE LOGITS

 unden

0.75

 alike

0.69

ItemImage

0.68

CVE

0.66

 effic

0.65

itarian

0.65

ç·

0.64

cent

0.63

artifacts

0.60

entimes

0.60

Activations Density 0.916%

phrases related to potential risks or issues

phrases or concepts related to uncertainty and risk

No Comments

No Known Activations