INDEX

Explanations

phrases related to events or actions that cause a strong reaction or response

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sparked" associated with events or reactions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ians

-0.70

esan

-0.69

 route

-0.66

 Controls

-0.61

 athlet

-0.60

 defeated

-0.60

ibble

-0.59

 rendered

-0.59

 Collector

-0.59

 wives

-0.58

POSITIVE LOGITS

 havoc

0.90

 pandemonium

0.86

actionDate

0.85

TextColor

0.83

rings

0.80

 uproar

0.78

 anew

0.76

LEASE

0.74

 anger

0.73

ItemTracker

0.72

Activations Density 0.066%

phrases related to events or actions that cause a strong reaction or response

instances of the word "sparked" associated with events or reactions

No Comments

No Known Activations