INDEX

Explanations

instances where someone turns down an opportunity or suggestion

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

eve

-0.66

arij

-0.66

ockey

-0.65

awar

-0.65

arc

-0.65

forces

-0.64

ivil

-0.64

inki

-0.64

war

-0.64

truth

-0.64

POSITIVE LOGITS

 invitations

1.07

 requests

1.02

 bids

0.96

 bribes

0.95

 advances

0.92

 permission

0.90

 temptation

0.89

 bidding

0.88

 pleas

0.86

 suggestions

0.86

Activations Density 0.076%

instances where someone turns down an opportunity or suggestion

No Comments

No Known Activations