INDEX

Explanations

words related to leaving or ending a situation or place

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

gall

-0.74

Cho

-0.70

venants

-0.66

cheat

-0.65

ibr

-0.59

anon

-0.57

peer

-0.57

orial

-0.56

ested

-0.55

etheless

-0.55

POSITIVE LOGITS

 sake

2.19

 purposes

1.92

 reasons

1.40

ummies

1.32

 purpose

1.23

 foreseeable

1.02

 reason

1.02

 duration

0.94

 Reasons

0.90

ulz

0.89

Activations Density 1.818%

words related to leaving or ending a situation or place

No Comments

No Known Activations