INDEX

Explanations

terms related to affection, admiration, or preference towards something or someone

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

avis

-0.61

 Noon

-0.61

ilib

-0.60

 transitions

-0.58

 Degree

-0.57

å¸

-0.56

 disruptive

-0.56

 cumbers

-0.56

 Extras

-0.55

 briefings

-0.55

POSITIVE LOGITS

 passionately

0.92

rend

0.85

wart

0.84

atical

0.83

joy

0.83

lead

0.81

leader

0.80

uay

0.79

 uncond

0.79

bear

0.78

Activations Density 2.471%

terms related to affection, admiration, or preference towards something or someone

No Comments

No Known Activations