INDEX

Explanations

mentions of actions or activities related to playing

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

 Beir

-0.75

fty

-0.66

thening

-0.66

imb

-0.66

inki

-0.64

ortium

-0.62

pora

-0.61

ageddon

-0.59

mediately

-0.57

identally

-0.56

POSITIVE LOGITS

wright

1.19

ername

1.13

lists

0.91

GROUND

0.88

testing

0.87

testers

0.85

 Piano

0.84

plays

0.83

wr

0.81

 Solitaire

0.79

Activations Density 0.476%

mentions of actions or activities related to playing

No Comments

No Known Activations