INDEX

Explanations

terms related to hazards, especially workplace hazards

oai_token-act-pair · gpt-3.5-turbo

references to various types of hazards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ebus

-0.96

gdala

-0.95

ulet

-0.89

itton

-0.87

artney

-0.85

ivia

-0.84

het

-0.84

istors

-0.78

hetti

-0.74

ampires

-0.74

POSITIVE LOGITS

 hazards

1.12

 hazard

1.09

ously

0.97

 Hazard

0.89

 mitigation

0.82

sofar

0.71

ous

0.71

 Bunny

0.69

 unbeliev

0.68

saf

0.68

Activations Density 0.011%

terms related to hazards, especially workplace hazards

references to various types of hazards

No Comments

No Known Activations