INDEX

Explanations

personal possessive pronouns indicating ownership

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

apa

-0.67

 Dalai

-0.66

pedia

-0.66

 coroner

-0.66

Reviewer

-0.65

usp

-0.65

izu

-0.64

ozy

-0.61

 Observer

-0.61

 Gors

-0.61

POSITIVE LOGITS

own

1.22

 possessions

1.00

 belongings

0.94

own

0.90

 contemporaries

0.88

 peers

0.85

OWN

0.82

 predecessors

0.81

 income

0.81

 colleagues

0.81

Activations Density 0.090%

personal possessive pronouns indicating ownership

No Comments

No Known Activations