INDEX

Explanations

titles related to political figures and positions within the 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_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

crew

-0.79

MpServer

-0.73

pson

-0.63

nikov

-0.63

wed

-0.63

ward

-0.63

jiang

-0.63

 captcha

-0.62

fw

-0.62

::::::::

-0.61

POSITIVE LOGITS

 Shaun

1.21

 Steve

1.19

 Tony

1.18

 Stephen

1.17

 Colin

1.14

 Mike

1.13

 Alvin

1.11

 Michael

1.11

 Richard

1.11

 David

1.11

Activations Density 1.243%

titles related to political figures and positions within the government

No Comments

No Known Activations