INDEX

Explanations

terms related to public health

oai_token-act-pair · gpt-3.5-turbo

references to public health

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

pload

-0.81

coni

-0.75

 Goblin

-0.71

KER

-0.69

 Claus

-0.67

RAW

-0.67

ãĤ§

-0.66

google

-0.66

ked

-0.64

âķĲ

-0.64

POSITIVE LOGITS

 advis

0.95

 emergencies

0.86

 care

0.82

 awareness

0.80

 epidem

0.78

 hazard

0.78

 hazards

0.77

awareness

0.76

 practition

0.76

 oversight

0.76

Activations Density 0.028%

terms related to public health

references to public health

No Comments

No Known Activations