INDEX

Explanations

future events or plans

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

baugh

-0.75

ocker

-0.74

 Feldman

-0.73

ordes

-0.70

enance

-0.68

hess

-0.66

cks

-0.64

bred

-0.63

eers

-0.61

lees

-0.61

POSITIVE LOGITS

 week

1.16

 month

1.09

 year

0.99

 semester

0.95

 door

0.89

ĻĤ

0.83

yr

0.83

 generation

0.82

decade

0.81

 Month

0.79

Activations Density 0.028%

future events or plans

No Comments

No Known Activations