INDEX

Explanations

references to specific items and projects such as games, movies, and tournaments

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gerald

-0.71

awaru

-0.70

otle

-0.68

ured

-0.66

manship

-0.64

iership

-0.63

Ik

-0.63

urated

-0.63

rolet

-0.62

etz

-0.62

POSITIVE LOGITS

nd

2.14

ND

1.19

 thirds

1.06

0.99

0.98

0.95

 externalToEVAOnly

0.93

0.90

 halves

0.89

0.88

Activations Density 0.671%

references to specific items and projects such as games, movies, and tournaments

No Comments

No Known Activations