INDEX

Explanations

words related to lap events or situations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flavoring

-0.96

xual

-0.75

hood

-0.73

NESS

-0.70

 Fargo

-0.69

 Marketable

-0.68

ãĥ¼ãĥĨãĤ£

-0.67

ALLY

-0.67

selage

-0.66

merce

-0.65

POSITIVE LOGITS

ocobo

0.99

ipop

0.93

alos

0.93

robe

0.91

alm

0.91

dogs

0.91

dog

0.89

olit

0.89

Lap

0.82

chair

0.80

Activations Density 0.024%

words related to lap events or situations

No Comments

No Known Activations