INDEX

Explanations

references to large numbers or quantities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "thousands" indicating large quantities of people or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 symmetry

-0.63

bones

-0.63

 hegemony

-0.61

slot

-0.60

 fixation

-0.60

 Syndicate

-0.60

cer

-0.59

bid

-0.59

Sac

-0.58

Sov

-0.58

POSITIVE LOGITS

 thousands

0.93

 Thousands

0.88

ourcing

0.86

ousands

0.86

 millions

0.85

 ILCS

0.84

ourced

0.82

yrs

0.78

 Millions

0.78

ights

0.77

Activations Density 0.024%

references to large numbers or quantities

instances of the word "thousands" indicating large quantities of people or items

No Comments

No Known Activations