INDEX

Explanations

references to physical locations like rooms or areas

oai_token-act-pair · gpt-3.5-turbo

references to physical spaces and their attributes

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

Negative Logits

 vengeance

-0.80

 ransom

-0.72

 nerve

-0.71

 blackmail

-0.66

 serial

-0.66

 fireball

-0.63

 bastard

-0.63

awar

-0.62

 indictment

-0.62

ãĥ©ãĥ³

-0.61

POSITIVE LOGITS

 amenities

1.03

 seating

0.97

paces

0.96

 spaces

0.93

cape

0.88

 Spaces

0.88

 accommodations

0.86

 adjoining

0.83

hips

0.83

pace

0.81

Activations Density 0.196%

references to physical locations like rooms or areas

references to physical spaces and their attributes

No Known Activations