INDEX

Explanations

specific instances or actions mentioned in a document

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

natureconservancy

-0.84

inventoryQuantity

-0.82

 Alive

-0.74

iddler

-0.68

ylon

-0.67

 alive

-0.65

urity

-0.64

ingham

-0.63

 Plain

-0.62

 Trance

-0.61

POSITIVE LOGITS

 toward

1.31

 towards

1.21

 downwards

0.94

irection

0.93

 Towards

0.93

rils

0.92

ggle

0.87

 squarely

0.86

 downward

0.84

ges

0.83

Activations Density 1.092%

specific instances or actions mentioned in a document

No Comments

No Known Activations