INDEX

Explanations

mentions of the word "deaths"

oai_token-act-pair · gpt-3.5-turbo

references to "deaths" in various contexts

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

arity

-0.73

asonic

-0.69

kef

-0.67

venants

-0.66

nice

-0.65

wcsstore

-0.65

por

-0.64

artisan

-0.64

agall

-0.64

ellig

-0.64

POSITIVE LOGITS

 toll

0.87

 deaths

0.87

ffen

0.77

 Deaths

0.76

 overdoses

0.74

guard

0.73

 prematurely

0.71

 overdose

0.71

 expectancy

0.70

rs

0.68

Activations Density 0.053%

mentions of the word "deaths"

references to "deaths" in various contexts

No Comments

No Known Activations