INDEX

Explanations

negative descriptive adjectives preceded by a hyphen

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

 Dickinson

-0.72

çīĪ

-0.71

 privately

-0.71

ulhu

-0.69

 Sina

-0.65

 Anon

-0.65

HHS

-0.65

ND

-0.65

 Asia

-0.64

 moder

-0.64

POSITIVE LOGITS

sounding

1.59

looking

1.54

minded

1.38

enough

1.30

eyed

1.25

yet

1.15

ness

1.13

colored

1.12

footed

1.07

fe

1.06

Activations Density 0.057%

negative descriptive adjectives preceded by a hyphen

No Comments

No Known Activations