INDEX

Explanations

medical terms for body parts or medical conditions

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

cale

-0.93

creen

-0.76

nesday

-0.76

auga

-0.75

uits

-0.74

hirt

-0.73

aukee

-0.73

uce

-0.69

aurus

-0.68

ynski

-0.66

POSITIVE LOGITS

hood

0.99

 sizes

0.95

less

0.94

wise

0.94

holders

0.90

 registrations

0.90

makers

0.88

 makers

0.87

busters

0.85

lets

0.85

Activations Density 3.568%

medical terms for body parts or medical conditions

No Comments

No Known Activations