INDEX

Explanations

negative statements or warnings

oai_token-act-pair · gpt-3.5-turbo

negations or words indicating the absence of something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¥

-0.67

 yeah

-0.64

lined

-0.63

Tow

-0.62

 Guys

-0.60

 Stuff

-0.60

 Steps

-0.60

quickShipAvailable

-0.59

 Corner

-0.59

Way

-0.59

POSITIVE LOGITS

icably

1.18

 necessarily

1.18

icable

1.03

hin

1.00

necess

0.94

yet

0.93

 adequately

0.88

epad

0.84

 exist

0.81

 hesitate

0.81

Activations Density 0.193%

negative statements or warnings

negations or words indicating the absence of something

No Comments

No Known Activations