INDEX

Explanations

personal pronouns indicating possession

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

etheless

-0.80

IVERS

-0.67

andel

-0.58

amily

-0.57

 Jacobs

-0.53

 cancellation

-0.53

NM

-0.52

mary

-0.52

 Physicians

-0.50

 Nichols

-0.50

POSITIVE LOGITS

1.29

panic

1.22

1.05

 Majesty

1.05

or

0.96

/_

0.92

 Honour

0.90

/,

0.89

/.

0.89

/#

0.88

Activations Density 0.229%

personal pronouns indicating possession

No Comments

No Known Activations