INDEX

Explanations

pronouns or related words indicating oneself or a group

oai_token-act-pair · gpt-3.5-turbo

references to personal pronouns and self-reference

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Applications

-0.65

Closure

-0.65

 Finish

-0.64

:{

-0.59

Record

-0.58

 Doors

-0.58

ulton

-0.57

 Congo

-0.56

 recess

-0.56

 MUCH

-0.56

POSITIVE LOGITS

adow

1.17

adows

1.09

andering

1.07

imei

1.06

atically

1.05

anwhile

1.02

aning

0.96

atic

0.96

hers

0.94

atics

0.93

Activations Density 0.091%

pronouns or related words indicating oneself or a group

references to personal pronouns and self-reference

No Comments

No Known Activations