INDEX

Explanations

medical terms or locations

oai_token-act-pair · gpt-3.5-turbo

references to medical and media institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inventoryQuantity

-0.82

ibly

-0.79

written

-0.78

å£

-0.76

 diaper

-0.72

IBLE

-0.72

arted

-0.70

yt

-0.70

trump

-0.69

posted

-0.69

POSITIVE LOGITS

 Disorders

0.95

 Areas

0.95

 Disorder

0.95

 Library

0.94

 Conference

0.94

 Guys

0.93

 Practice

0.92

 Solutions

0.92

 Madness

0.92

 Association

0.91

Activations Density 0.069%

medical terms or locations

references to medical and media institutions

No Comments

No Known Activations