INDEX

Explanations

medical conditions or related terms

oai_token-act-pair · gpt-3.5-turbo

references to medical conditions and related terminology

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

externalActionCode

-0.80

ectar

-0.75

zees

-0.73

Reviewer

-0.72

soDeliveryDate

-0.69

ilet

-0.68

steen

-0.68

selage

-0.67

\\\\\\\\

-0.64

tip

-0.64

POSITIVE LOGITS

 disorders

1.02

 diseases

1.01

 diagnosed

0.96

ascular

0.96

 diagnoses

0.95

 worsened

0.94

 symptoms

0.91

 Symptoms

0.89

 disease

0.89

 vascular

0.86

Activations Density 0.072%

medical conditions or related terms

references to medical conditions and related terminology

No Comments

No Known Activations