INDEX

Explanations

references to technical or professional communication, such as emails and instructions

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

 redu

-0.70

wagen

-0.68

 piping

-0.67

 ratios

-0.67

 halfway

-0.67

 seams

-0.66

 factories

-0.66

 reckoning

-0.65

 rooft

-0.65

 regression

-0.65

POSITIVE LOGITS

?]

1.68

!]

1.54

sic

1.50

REDACTED

1.40

âĢ¦]

1.36

 edit

1.34

...]

1.32

email

1.29

](

1.28

actionDate

1.24

Activations Density 0.384%

references to technical or professional communication, such as emails and instructions

No Comments

No Known Activations