INDEX

Explanations

technology-related terms and concepts

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

 Graves

-0.66

 empt

-0.65

 Beir

-0.64

Wem

-0.63

 Ambrose

-0.63

 duty

-0.62

rict

-0.61

 Mara

-0.61

 Returning

-0.61

 Duty

-0.61

POSITIVE LOGITS

 savvy

1.02

Crunch

0.99

 gadgets

0.92

 gadget

0.89

netic

0.89

 glitches

0.87

puting

0.85

 algorithms

0.84

 innov

0.84

 specs

0.82

Activations Density 2.456%

technology-related terms and concepts

No Comments

No Known Activations