INDEX

Explanations

positive adjectives related to quality

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

 Zamb

-0.68

ĸļ

-0.64

 Adin

-0.64

 duly

-0.63

 Slater

-0.60

 Sheriff

-0.60

 Nieto

-0.60

cific

-0.56

 complimentary

-0.56

hov

-0.55

POSITIVE LOGITS

ainment

1.04

astic

0.92

ech

0.91

ournament

0.89

astical

0.88

itious

0.85

hent

0.84

hetical

0.80

ures

0.79

agraph

0.76

Activations Density 0.050%

positive adjectives related to quality

No Comments

No Known Activations