INDEX

Explanations

references to medical professionals, particularly doctors

oai_token-act-pair · gpt-3.5-turbo

references to medical professionals, specifically doctors

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

yss

-0.72

*/(

-0.67

cluding

-0.64

 Huff

-0.63

issan

-0.62

AW

-0.62

CHAT

-0.62

ndra

-0.61

theless

-0.61

 Flavoring

-0.61

POSITIVE LOGITS

doctor

1.09

 doctor

1.05

 physician

0.88

 examiner

0.87

 Doctor

0.86

 practitioner

0.80

iate

0.78

abase

0.78

killer

0.78

Doctor

0.78

Activations Density 0.013%

references to medical professionals, particularly doctors

references to medical professionals, specifically doctors

No Comments

No Known Activations