INDEX

Explanations

information and research related to mental health and personality traits

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

 Canaver

-0.91

 Tomorrow

-0.71

ufact

-0.66

pload

-0.66

dump

-0.65

laun

-0.63

 Towns

-0.63

emonium

-0.63

Boot

-0.63

abad

-0.63

POSITIVE LOGITS

 interpersonal

1.25

 subjective

1.12

 characteristic

1.09

 physiological

1.08

 factors

1.08

 behavioral

1.07

 correlated

1.05

 stereotyp

1.05

 characteristics

1.04

 perceptual

1.04

Activations Density 0.643%

information and research related to mental health and personality traits

No Comments

No Known Activations