INDEX

Explanations

terms related to moderating or being a moderator

oai_token-act-pair · gpt-3.5-turbo

terms related to moderation and moderators in discussions or panels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

INESS

-0.79

OTAL

-0.77

ITNESS

-0.76

 Lilly

-0.73

borne

-0.72

Tac

-0.72

 Winds

-0.70

usions

-0.67

urst

-0.66

ties

-0.66

POSITIVE LOGITS

 moder

1.22

 moderators

1.14

 moderator

1.01

 moderation

0.92

 Moder

0.86

 Bots

0.76

 spoiler

0.76

 tranquil

0.74

iquette

0.73

elist

0.71

Activations Density 0.027%

terms related to moderating or being a moderator

terms related to moderation and moderators in discussions or panels

No Comments

No Known Activations