INDEX

Explanations

parts of a document containing references to computer programming or code-related content

oai_token-act-pair · gpt-3.5-turbo

technical terms and identifiers related to programming and data structures

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

ĪĴ

-0.71

 Refuge

-0.71

clerosis

-0.69

acea

-0.66

 Taxi

-0.64

enegger

-0.64

 è£ıè

-0.63

 congestion

-0.62

\\\\\\\\

-0.60

isp

-0.60

POSITIVE LOGITS

agall

0.99

sels

0.82

retty

0.77

tips

0.69

imately

0.67

atters

0.67

dit

0.66

onia

0.64

hent

0.63

ermott

0.63

Activations Density 0.504%

parts of a document containing references to computer programming or code-related content

technical terms and identifiers related to programming and data structures

No Comments

No Known Activations