INDEX

Explanations

profane words or vulgar language

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

lihood

-0.68

NING

-0.67

enegger

-0.67

nces

-0.65

Äĩ

-0.63

risome

-0.63

atical

-0.61

senal

-0.61

manship

-0.61

POL

-0.60

POSITIVE LOGITS

ogether

1.26

imore

1.20

itude

1.11

reatment

0.96

itudes

0.95

uve

0.92

zman

0.86

itud

0.82

ournament

0.81

ree

0.80

Activations Density 0.015%

profane words or vulgar language

No Comments

No Known Activations