INDEX

Explanations

negative or concerning situations or events

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

 fixme

-0.91

GET

-0.74

tarians

-0.72

WD

-0.72

aucuses

-0.68

XY

-0.68

tarian

-0.65

anooga

-0.65

pez

-0.65

imilation

-0.65

POSITIVE LOGITS

 clouds

1.13

 cloud

1.05

 haze

1.05

 shroud

1.03

 haunting

1.02

 gloom

1.02

 tarn

0.93

 hovering

0.92

 shrouded

0.91

 looming

0.91

Activations Density 0.160%

negative or concerning situations or events

No Comments

No Known Activations