INDEX

Explanations

words related to negative events such as attacks, crashes, and blasts

oai_token-act-pair · gpt-3.5-turbo

references to violent incidents or attacks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ophy

-0.71

anium

-0.68

uchin

-0.67

Intern

-0.67

 iodine

-0.64

hemy

-0.64

glomer

-0.63

anol

-0.63

 ILCS

-0.62

bil

-0.62

POSITIVE LOGITS

 spree

1.07

 occurred

0.86

 unfold

0.81

âĶĢâĶĢ

0.81

 rampage

0.80

 happened

0.79

 unfolded

0.78

 stemmed

0.78

 ordeal

0.77

 perpetrated

0.75

Activations Density 0.200%

words related to negative events such as attacks, crashes, and blasts

references to violent incidents or attacks

No Comments

No Known Activations