INDEX

Explanations

numbers with associated units of measurement

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

dain

-0.63

 Cosponsors

-0.59

ISA

-0.58

ellectual

-0.58

PDATE

-0.58

rency

-0.58

 rall

-0.56

rod

-0.56

estic

-0.55

Product

-0.54

POSITIVE LOGITS

0.69

0.68

0.67

0.65

ruct

0.65

0.64

Activations Density 0.668%

numbers with associated units of measurement

No Comments

No Known Activations