INDEX

Explanations

numbers, particularly either standalone or in pairs

oai_token-act-pair · gpt-3.5-turbo

lists of numerical data or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 antioxid

-0.70

 hemor

-0.70

 newsp

-0.64

 heartbeat

-0.61

 behavi

-0.61

 streng

-0.60

 advis

-0.60

 opin

-0.59

 attachments

-0.58

 nodd

-0.58

POSITIVE LOGITS

1.69

1.34

1.30

1.29

1.28

1.26

1.25

1.24

Activations Density 0.135%

numbers, particularly either standalone or in pairs

lists of numerical data or items

No Comments

No Known Activations