INDEX

Explanations

words related to security and assurance

oai_token-act-pair · gpt-3.5-turbo

words related to secure or safety-related states and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ingham

-0.88

soDeliveryDate

-0.77

ITNESS

-0.68

 pronounced

-0.59

 Trin

-0.58

ADS

-0.55

 heaviest

-0.53

 Dodgers

-0.53

tam

-0.53

email

-0.52

POSITIVE LOGITS

ures

1.04

URE

0.87

uring

0.84

ure

0.84

ured

0.82

tsky

0.82

witz

0.82

URES

0.77

mberg

0.76

anship

0.75

Activations Density 0.018%

words related to security and assurance

words related to secure or safety-related states and conditions

No Comments

No Known Activations