INDEX

Explanations

words related to the term "Id"

oai_token-act-pair · gpt-3.5-turbo

references to specific identifiers or labels, likely for entities or objects in the text

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

 guiActiveUnfocused

-0.75

 Kraken

-0.71

toe

-0.68

 Remastered

-0.68

 thinner

-0.67

 Saunders

-0.67

OUP

-0.67

ABLE

-0.63

SEA

-0.62

Ø©

-0.62

POSITIVE LOGITS

aho

1.32

iom

1.32

iots

1.24

entity

1.22

ividual

1.16

yll

1.16

leness

1.15

iop

1.10

iosyncr

1.07

iotic

1.03

Activations Density 0.012%

words related to the term "Id"

references to specific identifiers or labels, likely for entities or objects in the text

No Comments

No Known Activations