INDEX

Explanations

technical terms related to software settings and user configuration

oai_token-act-pair · gpt-4o-mini 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 funeral

-0.73

 dearly

-0.70

 starving

-0.69

 feud

-0.69

 weddings

-0.69

adan

-0.66

 doomed

-0.66

NPR

-0.65

 dope

-0.63

jad

-0.63

POSITIVE LOGITS

 Settings

0.98

 Browse

0.95

 Config

0.90

cknow

0.89

 Activate

0.89

 Scroll

0.88

menu

0.88

 Verify

0.88

 Preferences

0.88

 Properties

0.88

Activations Density 0.149%

technical terms related to software settings and user configuration

No Comments

No Known Activations