INDEX

Explanations

names of medical centers and hospitals

oai_token-act-pair · gpt-3.5-turbo

references to medical institutions and their various locations

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

xual

-0.89

uble

-0.80

spir

-0.74

arget

-0.72

wm

-0.70

rings

-0.69

dated

-0.68

hered

-0.68

*/(

-0.67

UAL

-0.66

POSITIVE LOGITS

 Sciences

1.07

 Services

0.94

 Association

0.89

 Corps

0.87

 Laboratory

0.85

 Solutions

0.84

 Care

0.84

 practition

0.84

 Research

0.84

 Complex

0.84

Activations Density 0.018%

names of medical centers and hospitals

references to medical institutions and their various locations

No Comments

No Known Activations