INDEX

Explanations

descriptions of specific physical attributes or characteristics of objects, especially related to design or features

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

dule

-0.89

usha

-0.63

ograms

-0.62

vertisements

-0.62

azine

-0.61

atories

-0.61

osures

-0.60

olitan

-0.59

admin

-0.59

neys

-0.59

POSITIVE LOGITS

 exacerbated

1.04

 contrasted

1.03

 manifested

1.01

 reflected

1.01

 evidenced

0.96

 compounded

0.93

 bolstered

0.89

 echoed

0.88

 coupled

0.88

 evident

0.86

Activations Density 2.126%

descriptions of specific physical attributes or characteristics of objects, especially related to design or features

No Comments

No Known Activations