INDEX

Explanations

terms related to clothing and accessories

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

actionDate

-0.82

Ļ½

-0.68

abama

-0.67

ync

-0.65

ãĥĥãĥī

-0.62

rians

-0.61

cffff

-0.61

NetMessage

-0.61

erenn

-0.60

cellaneous

-0.60

POSITIVE LOGITS

maker

1.07

 holder

1.04

holder

0.97

washer

0.95

 maker

0.94

holders

0.87

 pictured

0.86

Maker

0.83

wright

0.83

 cutter

0.82

Activations Density 2.135%

terms related to clothing and accessories

No Comments

No Known Activations