INDEX

Explanations

historical figures and events related to politics and government

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

 Lyft

-0.99

 emoji

-0.96

 Snapchat

-0.94

 takeaway

-0.94

 GoPro

-0.92

ï¸ı

-0.92

CNN

-0.91

(@

-0.89

FOX

-0.88

 veggies

-0.88

POSITIVE LOGITS

 postwar

1.22

 Protestant

1.14

1.13

1.12

1.11

 Ottoman

1.11

1.10

 Muss

1.09

1.08

Activations Density 4.185%

historical figures and events related to politics and government

No Comments

No Known Activations