INDEX

Explanations

words related to death, tragedy, and medical contexts

oai_token-act-pair · gpt-3.5-turbo

references to death and its associated consequences

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

soDeliveryDate

-0.82

soType

-0.76

ħĭ

-0.75

ãĥŃ

-0.74

utical

-0.74

wcsstore

-0.73

Ore

-0.72

actionDate

-0.72

eret

-0.72

lator

-0.71

POSITIVE LOGITS

 inquest

0.87

 autopsy

0.84

 coroner

0.82

 unborn

0.78

 Canaver

0.78

 gunshot

0.77

 overdose

0.76

 ransom

0.75

mur

0.74

 overdoses

0.73

Activations Density 0.473%

words related to death, tragedy, and medical contexts

references to death and its associated consequences

No Comments

No Known Activations