INDEX

Explanations

medical treatment-related phrases

oai_token-act-pair · gpt-3.5-turbo

references to medical treatment situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aer

-0.70

Export

-0.68

prints

-0.66

 Bour

-0.65

erd

-0.62

zyme

-0.61

sky

-0.60

crypt

-0.59

 crisp

-0.59

rake

-0.59

POSITIVE LOGITS

 treatment

1.26

 Treatment

1.18

reatment

1.08

 treatments

1.08

treatment

1.07

 therapies

0.88

ilitating

0.86

ttes

0.86

illance

0.83

 therapy

0.79

Activations Density 0.012%

medical treatment-related phrases

references to medical treatment situations

No Comments

No Known Activations