INDEX

Explanations

possessive pronouns followed by words related to personal experiences

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns indicating relationships and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

inctions

-0.91

yip

-0.66

 Poles

-0.66

 Israelis

-0.65

 Europeans

-0.64

witch

-0.62

seekers

-0.62

stall

-0.61

ifact

-0.61

lett

-0.59

POSITIVE LOGITS

 midst

1.37

 favor

1.30

 vicinity

1.24

 favour

1.23

 stead

1.20

 backyard

1.19

 bloodstream

1.10

 veins

1.04

 pocket

0.99

 inbox

0.98

Activations Density 0.129%

possessive pronouns followed by words related to personal experiences

possessive pronouns indicating relationships and ownership

No Comments

No Known Activations