INDEX

Explanations

mentions of possessive pronouns and related possessive terms

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

-0.78

vine

-0.78

haus

-0.74

 Izan

-0.70

 Unsure

-0.69

otin

-0.68

river

-0.68

 Frazier

-0.67

 Recomm

-0.64

bender

-0.63

POSITIVE LOGITS

own

2.14

 respective

1.33

OWN

1.25

self

1.25

 rightful

1.18

 newfound

1.18

 predecessors

1.17

 namesake

1.16

 surroundings

1.14

 usual

1.13

Activations Density 1.671%

mentions of possessive pronouns and related possessive terms

No Comments

No Known Activations