INDEX

Explanations

threats or acts of destruction

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

fman

-0.90

ensical

-0.75

gomery

-0.71

egal

-0.71

yrinth

-0.66

anooga

-0.66

ItemThumbnailImage

-0.65

Sop

-0.64

heid

-0.64

ruciating

-0.64

POSITIVE LOGITS

 ashore

0.86

out

0.86

 wiped

0.84

awa

0.83

off

0.82

down

0.82

 away

0.82

 wiping

0.81

 wipes

0.80

brush

0.80

Activations Density 0.032%

threats or acts of destruction

No Comments

No Known Activations