INDEX

Explanations

medical and psychiatric terms related to diagnosis and testing

oai_token-act-pair · gpt-3.5-turbo

terms related to diagnostic criteria and assessments in mental health

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

yss

-0.90

JO

-0.71

nesday

-0.69

erker

-0.69

uble

-0.69

orld

-0.69

cow

-0.68

 GOODMAN

-0.66

ffield

-0.65

pload

-0.64

POSITIVE LOGITS

ostics

1.50

ostic

1.31

 Diagn

1.00

 diagnoses

0.99

 diagn

0.89

 diagnosis

0.87

agn

0.87

oses

0.83

osis

0.83

abetes

0.77

Activations Density 0.015%

medical and psychiatric terms related to diagnosis and testing

terms related to diagnostic criteria and assessments in mental health

No Comments

No Known Activations