INDEX

Explanations

words related to train "derailment."

oai_token-act-pair · gpt-3.5-turbo

references to train accidents and their impacts

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

ternity

-0.73

orneys

-0.71

umption

-0.70

 Kinnikuman

-0.70

iping

-0.69

ervation

-0.68

isations

-0.66

archs

-0.65

estate

-0.65

anamo

-0.62

POSITIVE LOGITS

 derail

1.52

 derailed

1.17

 Amtrak

0.81

wagon

0.79

crew

0.75

ments

0.74

heimer

0.72

 freight

0.71

 Kinder

0.69

wreck

0.68

Activations Density 0.008%

words related to train "derailment."

references to train accidents and their impacts

No Comments

No Known Activations