INDEX

Explanations

questions and inquiries

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

interstitial

-0.63

Bey

-0.61

hyde

-0.58

said

-0.58

outed

-0.57

mun

-0.56

apsed

-0.56

ERG

-0.55

PT

-0.54

esp

-0.52

POSITIVE LOGITS

soever

1.05

 Does

0.91

ever

0.86

?!

0.84

do

0.83

Does

0.82

 does

0.81

 exactly

0.78

!?

0.77

Activations Density 0.900%

questions and inquiries

No Comments

No Known Activations