INDEX

Explanations

phrases related to blocking or restricting access to something

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

rious

-0.74

lli

-0.67

gow

-0.67

 Volunte

-0.66

BUS

-0.66

enture

-0.66

mble

-0.63

EMBER

-0.63

ospital

-0.62

elt

-0.61

POSITIVE LOGITS

buster

1.05

aded

0.99

ades

0.98

quote

0.95

busters

0.94

ading

0.90

ade

0.86

 access

0.79

 blocking

0.78

picking

0.72

Activations Density 0.031%

phrases related to blocking or restricting access to something

No Comments

No Known Activations

phrases related to blocking or restricting access to something

No Comments

No Known Activations