INDEX

Explanations

instructions for performing specific tasks or operations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.79

brew

-0.68

pac

-0.57

bole

-0.56

Wire

-0.56

 pecul

-0.56

pron

-0.56

mot

-0.55

abet

-0.55

sim

-0.54

POSITIVE LOGITS

ificate

0.70

Ð»

0.67

 into

0.64

igate

0.63

owship

0.62

ative

0.62

Ñĭ

0.61

DPR

0.60

ezvous

0.60

querade

0.60

Activations Density 0.096%

instructions for performing specific tasks or operations

No Comments

No Known Activations