INDEX

Explanations

text related to historical events, particularly wars and battles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Palest

-0.79

 Kessler

-0.67

eele

-0.62

 fortun

-0.62

 Adin

-0.62

intern

-0.62

etsy

-0.58

 Nept

-0.57

å£

-0.57

 Strat

-0.56

POSITIVE LOGITS

<-

0.71

vernight

0.70

ONSORED

0.69

 caption

0.68

//[

0.67

SourceFile

0.63

malink

0.58

htaking

0.58

requisite

0.58

endif

0.58

Activations Density 2.339%

text related to historical events, particularly wars and battles

No Comments

No Known Activations