INDEX

Explanations

host-related words or terms

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

 Rite

-0.72

istar

-0.67

 msec

-0.63

 pave

-0.62

iage

-0.60

 prud

-0.60

 braking

-0.60

pend

-0.58

 Imper

-0.58

 shortcut

-0.57

POSITIVE LOGITS

esses

1.05

ilities

0.99

ess

0.92

names

0.86

ility

0.83

itors

0.82

name

0.82

el

0.80

emark

0.79

Guest

0.78

Activations Density 0.813%

host-related words or terms

No Comments

No Known Activations