INDEX

Explanations

references to locations, political conversations, and technical product features

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

SHIP

-0.69

 Moonlight

-0.66

AFL

-0.65

beans

-0.62

FTA

-0.60

soever

-0.60

 Jinn

-0.60

doms

-0.60

OLOGY

-0.59

 Emmanuel

-0.59

POSITIVE LOGITS

ayed

1.28

phi

1.21

aware

1.17

usional

1.17

icate

1.16

ivered

1.15

ivery

1.15

ivering

1.14

inqu

1.10

iber

1.09

Activations Density 0.012%

references to locations, political conversations, and technical product features

No Comments

No Known Activations