INDEX

Explanations

phrases related to medical procedures and patient care

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

HCR

-0.69

Trend

-0.64

 behaviours

-0.60

 appropri

-0.60

kson

-0.59

anwhile

-0.59

lements

-0.59

CHAT

-0.58

Interstitial

-0.58

 Caption

-0.57

POSITIVE LOGITS

heartedly

0.96

 dozen

0.88

dozen

0.82

wheel

0.81

pipe

0.81

imet

0.78

terness

0.74

hearted

0.73

wit

0.73

plet

0.73

Activations Density 1.044%

phrases related to medical procedures and patient care

No Comments

No Known Activations