INDEX

Explanations

phrases related to possession or ownership

oai_token-act-pair · gpt-3.5-turbo

references to possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

vine

-0.83

 Unsure

-0.77

AAAA

-0.72

haus

-0.71

/+

-0.70

JB

-0.70

atoon

-0.67

spe

-0.67

 Zoom

-0.67

ozy

-0.67

POSITIVE LOGITS

own

1.89

 respective

1.56

selves

1.30

self

1.14

 rightful

1.14

 newfound

1.12

 selves

1.12

 lives

1.06

 entire

1.04

 surroundings

1.03

Activations Density 0.211%

phrases related to possession or ownership

references to possession or ownership

No Comments

No Known Activations