INDEX

Explanations

words related to numbers, especially when it comes to quantification or mathematical operations

oai_token-act-pair · gpt-3.5-turbo

references to numerical values or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rador

-1.16

ovie

-0.76

hire

-0.76

INTON

-0.76

robe

-0.74

rait

-0.70

Interstitial

-0.69

erate

-0.68

ossier

-0.68

clair

-0.68

POSITIVE LOGITS

 digits

0.81

plates

0.80

ames

0.77

 Numbers

0.72

 milliseconds

0.69

codes

0.69

 numer

0.69

metry

0.68

 comput

0.68

ology

0.67

Activations Density 0.036%

words related to numbers, especially when it comes to quantification or mathematical operations

references to numerical values or quantities

No Comments

No Known Activations