INDEX

Explanations

mentions of medical conditions or treatments related to patients

oai_token-act-pair · gpt-3.5-turbo

references to patients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

FLAG

-0.72

ģ«

-0.69

Politics

-0.67

GGGG

-0.63

POL

-0.62

shell

-0.62

Sharp

-0.61

BN

-0.61

ball

-0.61

sg

-0.60

POSITIVE LOGITS

 patients

1.12

 Patients

1.01

ients

1.00

 diagnosed

0.86

 patient

0.83

ysis

0.79

iatrics

0.78

 hospitalized

0.77

 afflicted

0.76

 smugglers

0.74

Activations Density 0.014%

mentions of medical conditions or treatments related to patients

references to patients

No Comments

No Known Activations