INDEX

Explanations

words related to current events and news articles

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

gdala

-0.82

vironment

-0.79

pheus

-0.79

uably

-0.77

ortium

-0.75

izon

-0.74

eryl

-0.74

liga

-0.74

izons

-0.71

oral

-0.70

POSITIVE LOGITS

 paced

1.48

idious

1.27

 pace

1.06

 turnaround

1.02

 speeds

0.97

running

0.94

 lear

0.90

 speed

0.87

 pacing

0.87

ened

0.85

Activations Density 0.767%

words related to current events and news articles

No Comments

No Known Activations