INDEX

Explanations

phrases related to doing tasks, activities, or actions

oai_token-act-pair · gpt-3.5-turbo

references to actions or behaviors being performed

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

 Dwell

-0.72

 Flavoring

-0.66

 sshd

-0.63

llah

-0.60

âĸĵ

-0.59

 Returning

-0.58

allion

-0.58

éŃĶ

-0.58

 ozone

-0.58

ixed

-0.57

POSITIVE LOGITS

 differently

1.09

 wrong

0.92

wrong

0.89

 unconsciously

0.85

 cheaply

0.82

 backwards

0.82

 responsibly

0.77

 offensively

0.76

 chores

0.76

 efficiently

0.76

Activations Density 0.109%

phrases related to doing tasks, activities, or actions

references to actions or behaviors being performed

No Comments

No Known Activations