INDEX

Explanations

words related to mental health conditions, specifically focusing on depression

oai_token-act-pair · gpt-3.5-turbo

references to depression and its related conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Sources

-0.94

Reply

-0.81

Grab

-0.79

source

-0.77

tnc

-0.77

leon

-0.75

SPONSORED

-0.73

quer

-0.72

xxxxxxxx

-0.70

Member

-0.69

POSITIVE LOGITS

 depression

1.10

 relapse

0.89

 depressive

0.87

 Depression

0.83

 disorder

0.81

 medication

0.79

 diagnosis

0.79

 distress

0.77

 depress

0.76

 worsen

0.76

Activations Density 0.014%

words related to mental health conditions, specifically focusing on depression

references to depression and its related conditions

No Comments

No Known Activations