INDEX

Explanations

technical terms related to data analysis and research

oai_token-act-pair · gpt-3.5-turbo

references to technical terms and categories related to systems, testing, and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 corrid

-0.64

BUG

-0.63

Reloaded

-0.63

iak

-0.62

armac

-0.60

Õ

-0.60

 looph

-0.59

 conqu

-0.59

Leaks

-0.58

 diversion

-0.57

POSITIVE LOGITS

hips

1.33

paces

1.19

 respectively

1.09

hip

1.06

pace

1.02

mith

0.97

ystem

0.96

 alike

0.95

etting

0.94

etter

0.93

Activations Density 0.602%

technical terms related to data analysis and research

references to technical terms and categories related to systems, testing, and structures

No Comments

No Known Activations