INDEX

Explanations

HTML code snippets

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

gaard

-0.72

issance

-0.67

pora

-0.66

 Stockholm

-0.65

ologne

-0.64

 Kuala

-0.63

reditary

-0.63

 installations

-0.63

EVA

-0.63

 Sabb

-0.62

POSITIVE LOGITS

></

1.37

><

1.27

}}

1.23

"></

1.19

">

1.18

/>

1.13

>"

1.13

"]=>

1.12

1.11

"]

1.11

Activations Density 0.408%

HTML code snippets

No Comments

No Known Activations