INDEX

Explanations

words related to physical properties or configurations

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

 CLIENT

-0.67

penter

-0.65

ewitness

-0.64

 Esper

-0.64

ynt

-0.63

vez

-0.63

 Targ

-0.62

BAT

-0.62

ega

-0.62

ople

-0.62

POSITIVE LOGITS

ername

0.89

nuts

0.81

tips

0.78

 folded

0.77

leaf

0.77

sheet

0.76

hered

0.74

tip

0.73

fold

0.72

past

0.72

Activations Density 0.031%

words related to physical properties or configurations

No Comments

No Known Activations