INDEX

Explanations

descriptions of conflicts and altercations between individuals

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

inventoryQuantity

-0.70

 resear

-0.65

Ago

-0.63

Lol

-0.60

 stag

-0.59

 rant

-0.58

icio

-0.58

 reputation

-0.57

 Demo

-0.56

TED

-0.56

POSITIVE LOGITS

 exchanged

0.97

 abound

0.97

 available

0.96

present

0.91

 forthcoming

0.91

 substituted

0.89

placed

0.86

 thrown

0.86

available

0.86

 inserted

0.84

Activations Density 2.911%

descriptions of conflicts and altercations between individuals

No Comments

No Known Activations