INDEX

Explanations

references to specific times or instances

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

 syndrome

-0.76

 Syndrome

-0.64

olson

-0.64

Question

-0.62

atur

-0.61

wind

-0.60

aud

-0.60

etc

-0.60

undrum

-0.58

 Question

-0.58

POSITIVE LOGITS

 accompanied

1.01

accompanied

0.90

 principally

0.88

 includ

0.85

 centered

0.82

 preceded

0.81

 primarily

0.78

 consisted

0.75

 aimed

0.73

 chiefly

0.72

Activations Density 2.126%

references to specific times or instances

No Comments

No Known Activations