INDEX

Explanations

references to fictional or real-world entities containing the word "Kill"

oai_token-act-pair · gpt-3.5-turbo

references to the film "Kill Bill" and related materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

issance

-0.83

herty

-0.70

rial

-0.69

 Indust

-0.68

ITED

-0.67

phrine

-0.65

acle

-0.65

bles

-0.63

 compr

-0.63

ritional

-0.62

POSITIVE LOGITS

joy

0.91

mails

0.87

adelphia

0.86

ingly

0.86

killer

0.86

guards

0.86

guard

0.82

req

0.82

mong

0.82

patrick

0.81

Activations Density 0.036%

references to fictional or real-world entities containing the word "Kill"

references to the film "Kill Bill" and related materials

No Comments

No Known Activations