INDEX

Explanations

phrases related to fairness and justice

oai_token-act-pair · gpt-3.5-turbo

concepts related to fairness and justice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

apse

-0.81

hent

-0.75

CHAT

-0.67

ember

-0.63

OUS

-0.63

 Underground

-0.63

acid

-0.61

OPLE

-0.60

artifacts

-0.60

uality

-0.60

POSITIVE LOGITS

yt

1.32

grounds

1.05

fair

0.87

ground

0.83

trade

0.80

eport

0.79

iciary

0.76

ies

0.75

parency

0.74

 compensation

0.73

Activations Density 0.052%

phrases related to fairness and justice

concepts related to fairness and justice

No Comments

No Known Activations