INDEX

Explanations

words related to online trolls

oai_token-act-pair · gpt-3.5-turbo

references to online trolling and trolls

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

 kosher

-0.69

 preservation

-0.66

 Colts

-0.64

 anesthesia

-0.63

++++++++++++++++

-0.62

 Continental

-0.61

 Mavericks

-0.59

 cider

-0.59

EVA

-0.58

 bonds

-0.58

POSITIVE LOGITS

 trolls

0.97

 troll

0.93

 trolling

0.88

ãĥĦ

0.86

tro

0.78

gren

0.75

ipedia

0.75

 Troll

0.75

atsuki

0.75

bag

0.74

Activations Density 0.016%

words related to online trolls

references to online trolling and trolls

No Comments

No Known Activations