INDEX

Explanations

phrases related to activity or involvement in a situation

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

 Beir

-0.74

fty

-0.66

inki

-0.65

imb

-0.64

thening

-0.63

pora

-0.63

ortium

-0.62

brow

-0.58

ageddon

-0.57

identally

-0.57

POSITIVE LOGITS

wright

1.15

ername

1.06

testing

0.86

lists

0.85

wr

0.83

GROUND

0.83

 Piano

0.83

 played

0.82

plays

0.81

testers

0.81

Activations Density 1.318%

phrases related to activity or involvement in a situation

No Comments

No Known Activations