INDEX

Explanations

phrases related to user login and authentication processes

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to login processes and user authentication

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahn

-0.74

 Judah

-0.68

mol

-0.64

oria

-0.64

TEXTURE

-0.63

×Ĳ

-0.62

olt

-0.61

aper

-0.61

 hurd

-0.61

Micro

-0.60

POSITIVE LOGITS

 credentials

1.13

 login

1.07

 Username

1.04

ccess

0.88

essed

0.86

 username

0.86

arantine

0.83

ession

0.82

login

0.78

istration

0.78

Activations Density 0.031%

phrases related to user login and authentication processes

terms and phrases related to login processes and user authentication

No Comments

No Known Activations