INDEX

Explanations

terms related to legitimacy

oai_token-act-pair · gpt-3.5-turbo

the concept of legitimacy or valid authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hani

-0.92

azel

-0.75

draw

-0.72

rix

-0.71

 Carbuncle

-0.70

ocket

-0.70

 Coat

-0.70

ilan

-0.69

berries

-0.68

 Daniels

-0.67

POSITIVE LOGITS

itimate

1.08

 legitimate

0.88

tarian

0.73

soDeliveryDate

0.70

DonaldTrump

0.69

acies

0.69

 guiActiveUn

0.69

²¾

0.68

 reason

0.67

 sounding

0.67

Activations Density 0.009%

terms related to legitimacy

the concept of legitimacy or valid authority

No Comments

No Known Activations