INDEX

Explanations

phrases related to readiness or preparedness

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

ĸļ

-0.74

ochet

-0.67

utra

-0.66

adish

-0.65

loss

-0.64

uo

-0.61

regate

-0.61

orb

-0.60

aura

-0.59

Publisher

-0.59

POSITIVE LOGITS

Ready

0.89

itude

0.88

 ready

0.84

 beforehand

0.78

atoon

0.77

 mentally

0.76

NESS

0.75

arity

0.73

 readiness

0.73

 Ready

0.73

Activations Density 0.889%

phrases related to readiness or preparedness

No Comments

No Known Activations