INDEX

Explanations

phrases related to specific topics or titles referenced in the 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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĹ¼

-0.94

 enthusi

-0.90

cffffcc

-0.83

ambo

-0.69

iating

-0.68

iscal

-0.66

Ò

-0.66

ufact

-0.65

ecd

-0.65

Redd

-0.64

POSITIVE LOGITS

 supra

0.79

 Strange

0.76

 Places

0.70

 Grave

0.69

 Corruption

0.68

 Gloss

0.66

 Submit

0.65

 Also

0.65

 Pinball

0.65

Unc

0.65

Activations Density 0.019%

phrases related to specific topics or titles referenced in the document

No Comments

No Known Activations