INDEX

Explanations

words related to mental health conditions and symptoms like schizophrenia, paranoia, delusions, and psychosis

oai_token-act-pair · gpt-3.5-turbo

terms related to mental health disorders and symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

neau

-0.83

ju

-0.76

phies

-0.74

AUT

-0.73

iers

-0.72

ributed

-0.70

toe

-0.69

fman

-0.68

yer

-0.67

mine

-0.66

POSITIVE LOGITS

 schizophren

1.08

 schizophrenia

0.98

 psychosis

0.93

 asylum

0.88

 Disorder

0.84

 disorder

0.84

 psychotic

0.81

 hallucinations

0.80

osis

0.79

ide

0.76

Activations Density 0.036%

words related to mental health conditions and symptoms like schizophrenia, paranoia, delusions, and psychosis

terms related to mental health disorders and symptoms

No Comments

No Known Activations