INDEX

Explanations

words related to legitimacy or lawful authority

oai_token-act-pair · gpt-3.5-turbo

the term "legitimate" and related context about legitimacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.79

azel

-0.78

emi

-0.73

hirt

-0.71

mith

-0.67

berries

-0.66

hire

-0.65

yi

-0.65

acid

-0.64

hene

-0.63

POSITIVE LOGITS

itimate

1.03

tarian

0.72

acies

0.71

 legitimate

0.71

 hunting

0.68

itable

0.68

 livelihood

0.67

 journalistic

0.67

 adult

0.66

00200000

0.66

Activations Density 0.028%

words related to legitimacy or lawful authority

the term "legitimate" and related context about legitimacy

No Comments

No Known Activations