INDEX

Explanations

prepositional phrases indicating a specific relationship between entities

oai_token-act-pair · gpt-3.5-turbo

references to independence or self-sufficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Relations

-0.61

APD

-0.60

Dialogue

-0.56

aukee

-0.55

ifax

-0.55

knit

-0.54

pod

-0.54

 Warfare

-0.53

sol

-0.53

halla

-0.52

POSITIVE LOGITS

 cost

1.17

 expense

0.99

 reason

0.96

 price

0.93

cost

0.90

Reason

0.89

 whim

0.84

 costs

0.84

 chance

0.82

 merit

0.80

Activations Density 0.455%

prepositional phrases indicating a specific relationship between entities

references to independence or self-sufficiency

No Comments

No Known Activations