INDEX

Explanations

mentions of notable events or achievements

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

Ö¼

-0.70

qus

-0.69

sequently

-0.69

ibo

-0.68

iph

-0.68

²¾

-0.65

opsis

-0.65

ulp

-0.65

venth

-0.64

_.

-0.64

POSITIVE LOGITS

 embattled

0.80

 pundits

0.69

 lawmakers

0.67

 Shinzo

0.67

 Rodrigo

0.65

 Sonny

0.64

 VICE

0.64

 comedian

0.63

 policymakers

0.63

 Canaver

0.63

Activations Density 0.234%

mentions of notable events or achievements

No Comments

No Known Activations

mentions of notable events or achievements

No Comments

No Known Activations