INDEX

Explanations

objects that can be used as weapons

oai_token-act-pair · gpt-3.5-turbo

instances of items or substances classified as dangerous or harmful

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

worldly

-0.81

Ĥª

-0.71

 nutshell

-0.68

thal

-0.68

issance

-0.68

prints

-0.63

istically

-0.63

izes

-0.63

jad

-0.62

ortment

-0.61

POSITIVE LOGITS

 which

0.73

etc

0.68

 Mehran

0.65

 tradem

0.61

Magikarp

0.59

 Mandal

0.58

Footnote

0.57

interrupted

0.57

 Delta

0.57

 Stronghold

0.56

Activations Density 0.256%

objects that can be used as weapons

instances of items or substances classified as dangerous or harmful

No Comments

No Known Activations