INDEX

Explanations

detailed technical information

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

aden

-0.78

 Nicaragua

-0.77

gate

-0.71

orea

-0.71

eno

-0.70

aneers

-0.69

oi

-0.68

enos

-0.68

ï¸

-0.67

Disney

-0.67

POSITIVE LOGITS

 detail

1.12

 descriptions

1.08

 details

1.03

 description

0.93

 information

0.92

 explanations

0.89

 examination

0.89

 outline

0.89

 deline

0.89

 outlines

0.88

Activations Density 0.033%

detailed technical information

No Comments

No Known Activations