INDEX

Explanations

timestamps or time indications

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

asty

-0.72

phen

-0.67

ancies

-0.64

 tomat

-0.64

urous

-0.63

oll

-0.62

ophe

-0.62

MIC

-0.61

bern

-0.61

krit

-0.60

POSITIVE LOGITS

ever

1.10

 ever

1.07

 EVER

1.05

 imaginable

0.90

 since

0.87

 anniversary

0.74

Ever

0.72

 practicable

0.68

 Ever

0.68

forth

0.67

Activations Density 0.022%

timestamps or time indications

No Comments

No Known Activations