INDEX

Explanations

descriptions of instances of sexual harassment and related incidents

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

aird

-0.77

vision

-0.72

chart

-0.69

zyme

-0.68

travel

-0.68

frames

-0.68

bits

-0.67

ellar

-0.66

itte

-0.65

ernels

-0.65

POSITIVE LOGITS

 perpetrated

1.22

 retaliation

1.01

 inflicted

1.01

 leveled

0.98

 blackmail

0.94

 accusations

0.93

 tactics

0.92

 abuse

0.91

 slurs

0.91

 against

0.91

Activations Density 2.886%

descriptions of instances of sexual harassment and related incidents

No Comments

No Known Activations