INDEX

Explanations

instances of personal experiences involving clothing and stains

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

 Cosponsors

-0.76

isSpecialOrderable

-0.75

 Canaver

-0.73

ERG

-0.69

 formally

-0.67

 Strategies

-0.66

MAP

-0.65

 Statements

-0.65

 Investigative

-0.64

ISC

-0.64

POSITIVE LOGITS

 chewing

0.91

nap

0.89

 pillow

0.88

?).

0.87

 litter

0.85

 chew

0.83

 snack

0.83

 toilet

0.83

)).

0.83

 laundry

0.81

Activations Density 0.595%

instances of personal experiences involving clothing and stains

No Comments

No Known Activations