INDEX

Explanations

information related to medical conditions or research studies involving people

oai_token-act-pair · gpt-3.5-turbo

references to human subjects or individuals in medical or psychological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãĥķãĤ©

-0.88

Chain

-0.78

Accessory

-0.78

èĢħ

-0.78

Rules

-0.77

Shut

-0.77

 actionGroup

-0.77

Viol

-0.76

é»Ĵ

-0.75

Politics

-0.75

POSITIVE LOGITS

 diagnosed

1.09

 aged

1.03

 ingested

1.01

 undergoing

1.00

opausal

1.00

 hormone

0.96

 studied

0.92

 hospitalized

0.92

 enrolled

0.89

 vaccinated

0.89

Activations Density 0.198%

information related to medical conditions or research studies involving people

references to human subjects or individuals in medical or psychological contexts

No Comments

No Known Activations