INDEX

Explanations

terms related to technical details and explanations, such as mechanisms and processes

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

 understatement

-0.81

audi

-0.72

illard

-0.69

 pics

-0.69

tics

-0.68

Politics

-0.67

iots

-0.66

rosso

-0.66

 Streets

-0.65

å§«

-0.64

POSITIVE LOGITS

 resembling

1.05

 consisting

1.03

shaped

0.90

like

0.89

 called

0.83

 containing

0.81

 akin

0.79

 periodically

0.78

 shaped

0.77

 whereby

0.76

Activations Density 0.406%

terms related to technical details and explanations, such as mechanisms and processes

No Comments

No Known Activations