INDEX

Explanations

possessive pronouns indicating ownership or association

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

ocument

-0.69

vine

-0.66

 Izan

-0.65

ablishment

-0.65

haus

-0.64

 along

-0.64

river

-0.64

 Provided

-0.64

ablish

-0.62

bender

-0.61

POSITIVE LOGITS

own

1.91

self

1.19

selves

1.15

OWN

1.13

 usual

1.07

Own

1.03

 newfound

1.01

 knees

1.00

 rightful

1.00

 respective

0.99

Activations Density 0.816%

possessive pronouns indicating ownership or association

No Comments

No Known Activations