INDEX

Explanations

words related to authentication techniques and procedures

oai_token-act-pair · gpt-3.5-turbo

terms and references related to authentication processes

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

ogue

-0.68

 Foods

-0.66

 Noct

-0.65

apers

-0.64

 Canaver

-0.64

 Abbott

-0.63

ttes

-0.63

neys

-0.62

borough

-0.62

prime

-0.60

POSITIVE LOGITS

 credentials

0.95

 authent

0.94

 authentication

0.90

orship

0.89

 handshake

0.84

 auth

0.83

token

0.79

Token

0.79

ications

0.76

 Authentication

0.76

Activations Density 0.034%

words related to authentication techniques and procedures

terms and references related to authentication processes

No Comments

No Known Activations