INDEX

Explanations

phrases related to mental health

oai_token-act-pair · gpt-3.5-turbo

terms related to mental health evaluations and care

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.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

SN

-0.90

 Collider

-0.79

Ô

-0.72

ISO

-0.65

 Towns

-0.65

è¦ļéĨĴ

-0.64

çĦ

-0.64

rawdownloadcloneembedreportprint

-0.63

dry

-0.63

Gig

-0.62

POSITIVE LOGITS

ilitating

0.87

 disorder

0.85

 counseling

0.84

 disorders

0.84

 counselors

0.81

 counselor

0.81

 examiner

0.81

aceutical

0.78

 diagnoses

0.78

ishop

0.75

Activations Density 0.043%

phrases related to mental health

terms related to mental health evaluations and care

No Comments

No Known Activations