INDEX

Explanations

references to cybersecurity terms, organizations, and activities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WARD

-0.85

patrick

-0.78

ships

-0.75

erness

-0.70

 Morty

-0.67

 Palmer

-0.65

 wagon

-0.65

landish

-0.64

holding

-0.64

ãģ¦

-0.62

POSITIVE LOGITS

posium

1.66

phony

1.29

ptoms

1.27

pt

1.01

pton

0.92

pta

0.91

anches

0.89

antics

0.89

ph

0.88

etrical

0.84

Activations Density 0.020%

references to cybersecurity terms, organizations, and activities

No Comments

No Known Activations