INDEX

Explanations

keywords related to structures and systems within various contexts, particularly in programming and social systems

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

DUP

-0.65

bestos

-0.65

 Benghazi

-0.61

AUT

-0.61

oidal

-0.60

quickShipAvailable

-0.60

 antidepressants

-0.59

 Hait

-0.58

 Sparrow

-0.58

 Entered

-0.57

POSITIVE LOGITS

 themselves

0.71

 itself

0.69

lists

0.65

reciation

0.61

wiki

0.59

 nationwide

0.57

 worldwide

0.57

oaded

0.57

 anywhere

0.55

azeera

0.55

Activations Density 0.423%

keywords related to structures and systems within various contexts, particularly in programming and social systems

No Comments

No Known Activations