INDEX

Explanations

words related to personal qualities, desires, or reflections

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thinkable

-0.78

cair

-0.73

»Ĵ

-0.71

ghai

-0.68

orks

-0.66

renches

-0.66

amsung

-0.65

sequ

-0.65

inctions

-0.65

skirts

-0.64

POSITIVE LOGITS

 counterpart

0.81

 cousin

0.80

 choice

0.79

 buddies

0.77

 foray

0.76

aiden

0.74

Favorite

0.73

 buddy

0.73

 selves

0.72

 asset

0.70

Activations Density 0.219%

words related to personal qualities, desires, or reflections

No Comments

No Known Activations