INDEX

Explanations

phrases related to built-in features or functionalities

oai_token-act-pair · gpt-3.5-turbo

references to built-in features or components of devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

anches

-0.82

Ń·

-0.81

Mub

-0.78

channelAvailability

-0.75

 Carbuncle

-0.74

kk

-0.72

ICAN

-0.72

llan

-0.71

CENT

-0.70

Ĥª

-0.70

POSITIVE LOGITS

strument

0.77

verted

0.72

clusions

0.68

jury

0.67

ization

0.67

ode

0.64

wards

0.63

urance

0.63

 support

0.63

itive

0.62

Activations Density 0.027%

phrases related to built-in features or functionalities

references to built-in features or components of devices

No Comments

No Known Activations